Corso di laurea

artificial intelligence

Università degli studi di Bologna · 109 materie · 0 file condivisi

Il corso di Laurea Magistrale in Artificial Intelligence risponde alla forte richiesta dei settori produttivi più avanzati di formare figure professionali con un'elevata specializzazione nei metodi e negli strumenti dell'intelligenza artificiale, capaci quindi di affrontare la progettazione, la realizzazione e la gestione di prodotti e servizi altamente innovativi.

Per operare efficacemente, le figure professionali dovranno avere competenze organiche nei settori dell'intelligenza artificiale, approfondite in un contesto interdisciplinare che le metta in grado di abbracciare la vastità dei possibili domini applicativi, favorendo l'innovazione nei campi più disparati.

Il corso mira a fornire una solida base culturale scientifica di tipo trasversale, unita a competenze su aree fondanti e applicative dell'intelligenza artificiale quali machine learning, visione artificiale, trattamento del linguaggio naturale, data science, ottimizzazione, e sistemi di supporto alle decisioni. Nell'ottica interdisciplinare tipica dell'intelligenza artificiale, nel corso verrà dato spazio anche alle tematiche legate alle neuroscienze cognitive e alle problematiche etiche e sociali.

Il percorso formativo è ideato come continuazione degli studi di primo livello in scienza e ingegneria informatica. La peculiarità della disciplina dell'intelligenza artificiale e la sua interdisciplinarità rende il percorso adatto anche a studenti di altre lauree che abbiano acquisito una solida formazione scientifica di base. Al fine di garantire l'omogeneità della preparazione sono previsti due insegnamenti specifici, alternativi, in relazione alla tipologia di laurea e al curriculum di provenienza del candidato.

Il percorso formativo prevede l'insegnamento in lingua inglese, consentendo l'accesso anche a studenti provenienti da altri paesi e favorendo quindi l'integrazione e lo scambio di conoscenze in un contesto internazionale.

Al termine del corso lo studente acquisirà il titolo di Dottore Magistrale in Artificial Intelligence, nella classe LM-32 (Ingegneria Informatica) o nella classe LM-18 (Informatica), in accordo alla sua vocazione e alle sue prospettive occupazionali, che possono spaziare dal mondo delle aziende e dei servizi al mondo della ricerca teorica e applicata. Il corso dà accesso agli studi di terzo ciclo (Dottorato di ricerca e Scuola di Specializzazione) e a master universitari di secondo livello.

Il percorso formativo è articolato come segue:
- 9 insegnamenti caratterizzanti, affini ed integrativi, obbligatori che forniscono le competenze di base comuni nei campi dell'intelligenza artificiale;
- 3 insegnamenti a scelta caratterizzanti o affini che forniscono le competenze specialistiche su settori applicativi innovativi;
- insegnamenti seminariali e soft skills;
- tesi di laurea con possibilità di tirocinio in Italia o all'estero.



Presentazione del Corso di Studio

Ecco tutti i dettagli sul corso di laurea selezionato. Sul UniDocs troverai gli appunti condivisi dagli altri studenti del tuo corso di laurea, ordinati per materia. Ricordati che per poter visualizzare il materiale devi essere registrato al sito e possedere un numero di crediti sufficiente.

Sfoglia il materiale didattico

Con UniDocs hai l'opportunità di studiare insieme a tutto il tuo corso di laurea. Guadagna subito dei crediti, carica il materiale del tuo ultimo esame!
Più condividi, più tempo avrai per studiare con tutta la community!

Materie del corso

COGNITION AND NEUROSCIENCE 1° anno · 2° semestre · 6 CFU · M-PSI/02 · 0 file

At the end of the course, the student knows state-of-art human and animal research that uses neuroscience techniques to understand the cognitive and emotional aspects of the human mind and behavior. The student is able…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student knows state-of-art human and animal research that uses neuroscience techniques to understand the cognitive and emotional aspects of the human mind and behavior. The student is able to critically read experimental and theoretical studies of cognitive and affective neuroscience, to evaluate their methods and results, explain their significance, and apply such notions in the study and development of artificial intelligence systems.

Programma

Course Description
How does neural activity give rise to the mind? How do billions of neurons enable us to perceive the world, learn from experience, remember the past, make decisions, and guide our actions?
This course provides an advanced introduction to cognitive neuroscience, exploring how mental functions emerge from the activity of neural circuits. Through the integration of experimental evidence, computational theories, and state-of-the-art research methods, students will examine how cognition is implemented in the brain.
Particular emphasis is placed on the neural mechanisms of learning, prediction, and decision-making, from the cellular basis of neuronal communication to reinforcement learning, dopamine signaling, and contemporary computational approaches inspired by neuroscience. The course also introduces how principles derived from cognitive neuroscience have influenced modern artificial intelligence.
Learning Outcomes
Upon successful completion of the course, students will be able to:
explain the physiological and neural mechanisms underlying perception, learning, memory, and decision-making across multiple levels of analysis, from individual neurons to large-scale brain networks; describe the computational principles of reinforcement learning and discuss their neural implementation; understand and critically evaluate contemporary theories and empirical findings in cognitive neuroscience; interpret experimental designs and results from cognitive neuroscience studies, appreciating the strengths and limitations of different methodological approaches; formulate scientifically grounded hypotheses and propose experimental strategies to test them; appreciate the reciprocal influence between cognitive neuroscience and artificial intelligence.
Course Content
The course is divided into two teaching modules.
Module 1 (4 CFU)
Introduction to cognitive neuroscience: the relevance of cognitive neuroscience to Artificial Intelligence and the relationship between brain structure and cognitive function. Neurons, neural circuits, and neural systems: anatomy and physiology of the nervous system, neuronal communication, and the organization of large-scale neural networks. Reinforcement learning: principles of Pavlovian (prediction) and instrumental (control) learning. Neural mechanisms of learning and memory: neural plasticity. Computational mechanisms of learning: contiguity, contingency, surprise, and prediction errors. The reward prediction error hypothesis of dopamine From reinforcement learning to decision-making: neural mechanisms underlying goal-directed and habitual behaviour.
Module 2 (2 CFU)
Reinforcement learning (RL): from cognitive neuroscience to artificial intelligence Visual processing: from cognitive neuroscience to artificial intelligence
Previous knowledge required:
Prerequisite involves high-school knowledge of the anatomy and physiology of the Nervous System.
It is recommended to view the videos on Neuroscience Core concepts, freely available at the Society for Neuroscience website: https://www.brainfacts.org/core-concepts

Modalità d'esame

Examination
The examination assesses students' knowledge and understanding of the topics covered during the course.
The exam consists of a 60-minute written test comprising three open-ended questions:
Two questions on the topics covered in Module 1 (Prof. Starita). One question on the topics covered in Module 2 (Prof. di Pellegrino).
All answers must be written in English.
Each question is worth a maximum of 10 points, for a total of 30 points. The final grade is the sum of the scores obtained on the three questions. The "30 cum laude" distinction will be awarded only to students who obtain the maximum score (10/10) on each question.
During the examination, students may not consult lecture materials, textbooks, scientific articles, personal notes, electronic devices, or any other external resources.
The exam will be completed on the laboratory computers via the EOL platform, where students will write and submit their answers.
Students with Disabilities or Specific Learning Disorders (DSA)
Students with temporary or permanent disabilities or specific learning disorders (DSA) are encouraged to contact the relevant University office as soon as possible:
https://site.unibo.it/studenti-con-disabilita-e-dsa/en/for-students
Requests for examination adaptations must be submitted at least 15 days before the exam date to Prof. Starita. The proposed adaptations will be evaluated to ensure they are compatible with the learning objectives of the course.
Exam Registration
Students must register for the examination through the AlmaEsami system by the published deadline.
Students who experience technical difficulties preventing timely registration must contact the Segreteria Didattica before the registration deadline and notify Prof. Starita by email. Admission to the examination in these cases will be evaluated on an individual basis.
Evaluation criteria
The following criteria will be applied to evaluate each answer:
Analysis/critical thinking
Ability to select, consider, evaluate, the course material relevant to answering the question. Use of appropriate definitions for the concepts prompted by the exam questions. Understanding of relevant concepts, through proper analysis of the course material. Ability to synthesize and employ in an original way ideas from across the course. Discussion of relevant evidence to support assertions (e.g. discussion of experimental evidence, use of citations/references).
Structure
Clarity of introduction, body, and conclusion Clear, logical and well-organized flow of information.
Style
Precision of vocabulary and use of academic tone. Clarity and conciseness of sentences, with minimal verbosity. Use of appropriate grammar, sentence construction, paragraph structure.
Grade Registration
Examination results will be published on AlmaEsami, and grades will be officially registered five working days after publication.
Students wishing to refuse their grade must notify Prof. Starita by email within five working days of the publication of the results. If no communication is received within this period, the grade will be automatically registered.
Students may refuse a grade any number of times.
Use of Artificial Intelligence (AI)
Students are encouraged to use AI tools responsibly to support their learning, for example by generating summaries, clarifying concepts, creating practice questions, or self-assessing their understanding.
The use of AI or any other unauthorized assistance during the examination is strictly prohibited and constitutes a violation of academic integrity.

Testi di riferimento

Lecture slides and scientific articles will be available on Virtuale and will represent the core material needed to pass the exam.
For Module 1, the following readings are also recommended:
Papers
Brooks R, Hassabis D, Bray D, Shashua A. Turing centenary: Is the brain a good model for machine intelligence? Nature. 2012 Feb 22;482(7386):462-3. doi: 10.1038/482462a. PMID: 22358812. Hassabis, D., Kumaran, D., Summerfield, C., & Botvinick, M. (2017). Neuroscience-inspired artificial intelligence. Neuron, 95(2), 245-258. Schultz, W. (2016). Dopamine reward prediction error coding. Dialogues in clinical neuroscience, 18(1), 23-32. Dolan, R. J., & Dayan, P. (2013). Goals and habits in the brain. Neuron, 80(2), 312–325. https://doi.org/10.1016/j.neuron.2013.09.007
Book chapters
Gazzaniga, M. S., Ivry, R. B., & Mangun, G. R. (2014). Cognitive Neuroscience, The biology of the mind. Chapters: 1, 2 Kandel, E. R., Schwartz, J. H., Jessell, T. M., Siegelbaum, S., Hudspeth, A. J., & Mack, S. (Eds.). (2000). Principles of neural science. New York: McGraw-hill. Chapters 2, 4, 6, 7, 8, 15, 48, 65 Daw, N. D., & O’Doherty, J. P. (2014). Multiple systems for value learning. In Neuroeconomics (Chapter 21, pp. 393-410). Academic Press. Daw, N. D., & Tobler, P.N. (2014). Value Learning through Reinforcement: The Basics of Dopamine and Reinforcement Learning. In Neuroeconomics (Chapter 15, pp. 283-298). Academic Press. Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction. MIT press. Chapter 14, 15

Codice insegnamento 91247

COMBINATORIAL DECISION MAKING AND OPTIMIZATION 1° anno · 2° semestre · 6 CFU · ING-INF/05 · 0 file

At the end of the course, the student has an understanding of the most popular methods in operations research and artificial intelligence for modeling and solving complex combinatorial optimization problems such as…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student has an understanding of the most popular methods in operations research and artificial intelligence for modeling and solving complex combinatorial optimization problems such as constraint programming, integer linear programming, SAT and SMT.

Programma

Prerequisites
Problem solving in artificial intelligence (covered by 91248 - Fundamentals of Artificial Intelligence and Knowledge Representation), logic for computer science and basic notions of algorithms and programming preferably in Python (covered by B5726 - Languages and Algorithms for Artificial Intelligence), basic algebra and analysis.
Course topics
The first half of the course (Module 1) will introduce the fundamental concepts in Constraint Programming (CP) and Boolean Satisfiability (SAT), which are two general-purpose approaches in Artificial Intelligence (AI) to combinatorial decision making and optimization. The topics include:
Introduction to combinatorial decision making and optimization Modelling in CP Constraint propagation and global constraints Constructive tree search and propagation, branching heuristics, randomization and search restarts, Large Neighbourhood Search (LNS) The SAT problem and encoding in SAT Basic solving techniques (resolution, unit propagation, DPLL algorithm) Conflict-driven clause learning algorithms SAT encodings
The second half of the course (Module 2) will introduce the fundamentals of Satisfiability Modulo Theory (SMT), which is a generalization of SAT. The last part of the module will be about essential Operations Research results from Linear Programming (LP) and in particular Integer Linear Programming (ILP), by prioritizing the width of the covered area over the depth of the introduction. The topics include:
Satisfiability Modulo Theories (SMT) Eager vs lazy SMT encoding, the DPLL(T) algorithm SMT theory solvers and combinations of theories Linear Programming (LP) Simplex algorithm and duality Integer Linear Programming (ILP) Extensions and hybrid methods
The course will also host invited lectures by pioneer researchers in the field in order to provide a broader perspective on the AI-based approaches to combinatorial decision making and optimization.

Modalità d'esame

Students’ understanding of the course topics is assessed through a single in-person, paper-based written exam. If deemed necessary, the lecturers may require an additional oral exam. During the exam, the use of books, written notes, calculators, electronic devices, or any internet access is strictly prohibited. Academic misconduct will be handled in accordance with university policy. There will be four exam sessions each academic year: the first three in June, July and September, and the last in January/February. Exact dates will be announced during the course and published on AlmaEsami. To attend an exam session, students must register via AlmaEsami by the stated deadlines. The written exam is evaluated based on the correctness and completeness of the answers. Higher grades are awarded to students who demonstrate a good command of the subject, clear and concise writing, and the ability to apply concepts to solve problems. A failing grade is assigned when responses show substantial gaps in key concepts, unclear or inappropriate expression, or flawed reasoning that compromises the validity of the solution.
A passing grade may be rejected only once. The final grade will be the next passing grade obtained in a subsequent exam session.

Testi di riferimento

Lecture slides and bibliography of scientific articles provided by the teaching staff. Handbook of Constraint Programming. F. Rossi, P. van Beek, T. Walsh (eds), Elsevier Science, 2006. Handbook of Satisfiability. A. Biere, M. Heule, H. van Maaren, T. Walsh (eds), IOS Press, second edition, 2021.

Codice insegnamento 91762

DEEP LEARNING 1° anno · 2° semestre · 6 CFU · INF/01 · 0 file

At the end of the course, the student understands the foundational ideas, recent advances and application potential of deep neural systems. The student understands supervised and unsupervised techniques, basic neural…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student understands the foundational ideas, recent advances and application potential of deep neural systems. The student understands supervised and unsupervised techniques, basic neural topologies, methods for visualizing and understanding the behavior on neural nets, adversarial and generative techniques, reinforcement learning, and recurrent networks. The student is able to apply such technologies to solving classification problems in realistic domains.

Programma

The course begins with an introduction to Neural Networks and Deep Learning, focusing on their typical training mechanism: the backpropagation algorithm.
We will discuss the main types of neural networks: feedforward, convolutional, and recurrent, providing concrete examples and examining architectures that have proven useful for image processing, localization, segmentation, style transfer, text processing, and many other applications.
Techniques for visualizing the behavior of hidden neural units will be explored, including those related to deep dreams and inceptionism. We will also cover techniques for fooling neural networks and modern generative techniques, including recent diffusion models.
The final part of the course will be dedicated to an introduction to Deep Reinforcement Learning, with particular attention to designing agents for video games, autonomous driving, and other situations that require complex and adaptive intelligent behaviors.
The course is part of the integrated curriculum with Machine Learning from the Artificial Intelligence Studies Program. Knowledge of the following subjects is assumed:
Machine Learning Analysis Algebra Python

Modalità d'esame

Individual project on topics defined by the teacher.
The grade can be optionally integrated by an oral examination.
The assesment method may change in relation with the attendance.

Testi di riferimento

Suggested readings:
Dive into Deep Learning
I.Goodfellow, Y.Bengio, A.Courville. Deep Learning. MIT Press.
Specific pointers to on line material will be provided at each lesson, in addition to the slides of the course.

Codice insegnamento 91250

FUNDAMENTALS OF ARTIFICIAL INTELLIGENCE AND KNOWLEDGE REPRESENTATION 1° anno · 1° semestre · 12 CFU · ING-INF/05 · 0 file

At the end of the course, the student knows the main knowledge representation techniques and reasoning methods that underlie artificial intelligence problem solving. The student is able to develop simple solvers for…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student knows the main knowledge representation techniques and reasoning methods that underlie artificial intelligence problem solving. The student is able to develop simple solvers for artificial intelligence systems.

Programma

The course introduces the fundamental principles and methods used in Artificial Intelligence to solve problems, with a special focus on the search in the state space, planning, knowledge representation and reasoning, and on the methods for dealing with uncertain knowledge. The course will include hands-on labs and seminars on selected topics.
Prerequisites: user-level knowledge of a high-level programming language, in order to successfully understand case studies and applications presented during the lessons.
Part I (Module 1)
Module 1. AI Foundations Decision Making and Automated Planning The first module introduces the foundations of intelligent decision making and problem solving. Topics include the a broad introduction to Artificial Intelligence, AI paradigms, Trustworthy AI and the European AI Act. The module then covers uninformed and informed search strategies, basics of game playing (Minimax and Alpha-Beta pruning), Constraint Satisfaction Problems, automated planning techniques (STRIPS, GraphPlan, Partial Order Planning and Hierarchical Planning), and nature-inspired optimization methods, including Genetic Algorithms and Swarm Intelligence. Practical laboratories and project work complement the theoretical lectures.
Part II (Modules 2, 3):
Module 2. Knowledge Representation and Symbolic Reasoning The second module focuses on symbolic knowledge representation and reasoning. Students are introduced to First Order Logic, Logic Programming and Prolog, followed by ontologies, Description Logics, and Knowledge Graphs. The module also covers temporal reasoning, Event Calculus, rule-based systems, Complex Event Processing and Business Process Management. The final part explores how symbolic knowledge can be integrated with Foundation Models through Knowledge Graphs and Retrieval-Augmented Generation (RAG), providing an introduction to modern neuro-symbolic AI systems.
Module 3. Reasoning under Uncertainty The final module introduces probabilistic reasoning for intelligent systems operating under uncertainty. Topics include probability theory, Bayesian Networks, Hidden Markov Models and other probabilistic graphical models, conditional independence, d- separation, probabilistic inference (exact and approximate), causal reasoning and uncertainty management. The module concludes by discussing the role of probabilistic reasoning and uncertainty estimation in contemporary AI systems, including Foundation Models.

Modalità d'esame

The exam aims at assessing the student's knowledge and skills in the course topics and it consists of three independent parts:
Part I, covering Module 1; Part II, covering Modules 2; Part III, covering Module 3.

Testi di riferimento

A comprehensive list of textbooks is available on the Web site, and it is reported also in the course slides.
S. J. Russel, P. Norvig, Artificial Intelligence: A modern approach, Prentice Hall, International edition.
R. J. Brachman, H. J. Levesque, Knowledge Representation and Reasoning, Elsevier, 2004. F. Baader, D. Calvanese, D.L. McGuinness, D. Nardi, P.F. Patel-Schneider (editors), The description logic handbook: Theory, implementation, and applications, Cambridge University Press New York, NY, USA, 2007

Codice insegnamento 91248

IMAGE PROCESSING AND COMPUTER VISION 1° anno · 2° semestre · 6 CFU · ING-INF/05 · 0 file

At the end of the course, the student masters the basic algorithms, tools and systems for the management, processing and analysis of digital images. The student is able to design and develop simple systems oriented to…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student masters the basic algorithms, tools and systems for the management, processing and analysis of digital images. The student is able to design and develop simple systems oriented to real-world computer vision applications such as those requiring segmentation and classification of objects in digital images.

Programma

Prerequisites: calculus and linear algebra
Part 1
Introduction: basic definitions related to computer vision. An overview across major application domains.
Image formation and acquisition: geometry of image formation; lenses; field of view and depth of field; image sampling and quantization.
Spatial filtering: linear shift-invariant operators; mean and Gaussian filtering; median filtering; bilateral filtering.
Edge detection: image gradient; non-maxima suppression; Laplacian of Gaussian; Canny edge detector.
Local invariant features: detectors and descriptors; Harris Corners; scale-invariant features; SIFT features.
Instance detection: pattern matching; shape-based matching; Hough transform.
Part 2
Camera calibration: Intrinsic and extrinsic camera parameters; projective coordinates and perspective projection matrix; Zhang's algorithm; image warping and homographies between cameras.
Image classification: the case for and implication of data-driven computer vision; datasets; linear classifier as template matching; cross-entropy loss; gradient descent and stochastic gradient descent.
Image representations: Bag of Visual Words; representation learning for images; convolutional layers; pooling; batch normalization.
Successful CNNs: LeNet5; AlexNet; ZFNet; VGG; Inception v1 and v3; ResNet.
Regularization and training recipes: model capacity; learning rate schedulers; weight decay; label smoothing; dropout; data augmentations; FixRes; cutout; mix-up; cut-mix; PyTorch case study.
The theory is complemented by lab sessions. Lab sessions cover selected topics such as spatial filtering, local invariant features, camera calibration, image classification and transfer learning.

Modalità d'esame

Student assessment consists of two components: a written theoretical exam and a practical part. Written exam: the student will answer questions on the theory presented in the whole course. The written exam lasts 90 minutes. No supporting materials are allowed during the exam (e.g., notes, textbooks, etc.).
The minimum grade required to pass the written exam is 15. The maximum grade for the written exam is 24. To take the written exam, the student must register through the AlmaEsami portal. The grade for the written exam can be rejected only once.
Regarding the written exam, the use of AI is prohibited. Any use of AI constitutes a violation of academic integrity. Practical part: consists of two assignments, one for each part of the course. The maximum grade for the practical part is 7. The assignments MUST be completed in groups of 2 (maximum 3) students. The assignment must be uploaded through Virtuale. The cut-off dates to upload the assignments will be published on Virtuale.
For the practical part: limited and non-substantial use of AI is allowed as a support tool (e.g, code debug, code documentation). Substantial use of AI to complete parts of the project is not permitted (e.g., fully generate the code for a cell of the notebook). Use of AI tools must be explicitly declared by the students. Students are responsible for the delivered notebook. The final mark is calculated as the sum of the grades obtained in the written exam and the practical part. The minimum grade required for the exam to be officially recorded is 18.
The written exam and the practical part may be completed independently, in either order. When the student has passed both parts of the exam, the final mark will be registered on AlmaEsami.
Students with specific learning disorders (SLD) or temporary or permanent disabilities are advised to contact the relevant University office well in advance (https://site.unibo.it/studenti-con-disabilita-e-dsa/en). The office will propose any necessary accommodations to the students concerned; in any case, these accommodations must be submitted to the Professor for approval at least 15 days in advance. The Professor will assess their suitability also in relation to the learning objectives of the course.

Testi di riferimento

All the slides from the lectures of the course will be made available on the Virtuale platform. There is no official textbook; further details on some of the topics of the course can be found in:

  • Gonzalez, R. C., "Digital Image Processing", Pearson education, 2009.
  • Hartley, R., & Zisserman, A., "Multiple View Geometry in Computer vision". Cambridge university press, 2003.
  • http://d2l.ai/ - Aston Zhang and Zachary C. Lipton and Mu Li and Alexander J. Smola "Dive into Deep Learning", 2020
    Further readings, such as scientific papers and online resources, might be recommended during the lectures of the course.

Codice insegnamento 91254

INTRODUCTION TO COMPUTABILITY AND COMPLEXITY 1° anno · 2° semestre · 6 CFU · ING-INF/05 · 0 file

At the end of the course, the student has an understanding of the theoretical foundations of linguistic and algorithmic techniques used in the context of AI.

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student has an understanding of the theoretical foundations of linguistic and algorithmic techniques used in the context of AI.

Programma

The course gives first of all some rudiments of computability and complexity theory: Turing machines, undecidability, polynomial time computability, and NP-completeness. Towards the end of the course, we give a bird's eye view on computational learning theory: PAC Learning, learning via uniform convergence, the VC-Dimension.

Modalità d'esame

The exam is done via EOL, and consists of two parts:
In the first one, the student will be required to answer five multiple choice questions about the topics of the course. This counts for 1/3 of the final mark. In the second one, the student will be asked to solve three exercises. This counts for 2/3 of the final mark.

Testi di riferimento

[1] Sanjeev Arora and Boaz Barak, Computational Complexity: A Modern Approach. Cambridge University Press, 2009.
[2] Michael Kearns, Umesh. Vazirani. An Introduction to Computational Learning Theory. MIT Press, 1994.
[3] Shai Shalev-Shwartz and Shai Ben-David. Understanding Machine Learning: From Theory to Algorithms. Cambridge University Press, 2014.

Codice insegnamento B5026

INTRODUCTION TO LANGUAGES FOR ARTIFICIAL INTELLIGENCE 1° anno · 1° semestre · 6 CFU · ING-INF/05 · 0 file

At the end of the course, the student has an understanding of the main linguistic techniques used in the context of AI, including the main aspects related to functional, logic and constraint programming.

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student has an understanding of the main linguistic techniques used in the context of AI, including the main aspects related to functional, logic and constraint programming.

Programma

Module 1
Abstract machines. Python machine. Programming in Python: names and visibility, functions, immutable and mutable objects, basic data types (numbers, strings, tuples, lists, dictionaries), and their use in the solution of problems. Classes and objects. Methods and inheritance. Exceptions. Introduction to the library NumPy and its N-dimensional array objects.
Module 2
Introduction to mathematical logic. Unification. Resolution. Introduction to logic programming. Prolog languages. Constraint logic programming and concurrent constraint programming. Constraint programming. The language MiniZinc.

Modalità d'esame

As this course (Introduction to Languages for Artificial Intelligence) is part of the Integrated Course “Languages and Algorithms for Artificial Intelligence”, to get a grade in the gradebook, students have to
Pass Module 1 (binary outcome: pass/fail) with Prof. Lodi
Pass Module 2 (mark expressed in thirties, you need to obtain at least 18) with Prof. Gabbrielli
Pass the course “Introduction to Computability and Complexity” with Prof. Dal Lago (mark expressed in thirties, you need to obtain at least 18)
The three exams can be taken in any order, and positive marks are valid for an indefinite period.
The final grade is obtained as the arithmetic mean of the grades in Module 2 and the Course "Introduction to Computability and Complexity", rounded to the nearest natural number.
For each module, you will have four calls (i.e., four attempts) each academic year.
Module 1 will be assessed through a 2-hour Python programming test, with automatic correction on test cases, on the EOL platform. The test will evaluate students' ability to correctly solve simple procedural programming problems using Python (and the NumPy library).
The system will assign a score to each test case for each exercise. Reaching a score of 18/30 or higher will result in a “pass”, while a score below 18/30 will result in a “fail” (the numerical score is not recorded).
The test will be held in the University laboratories, and students will have access to an IDE and to the documentation of Python and NumPy. No other websites or any documentation can be accessed (closed books).
A preliminary test could be offered at the end of October / early November. Other calls will be in Winter, Summer, and Autumn.
Following the lectures is crucial to understanding the theoretical concepts. For those who are unable to attend, recordings will be made available. Several exercises that do not contribute to the grade are provided for personal training. Doing the exercises assigned each week on Virtuale is crucial for learning the required programming skills. The automatic evaluation on test cases is a first relevant help. Tutors and the main instructor are also available for clarification.
Module 2 will be evaluated by menas of a written exam consisting of 6 exercises on the different part of the course, to be done in 2 hours.It is important to attend the lectures in order to practice with the exam exercises.

Testi di riferimento

Module 1
No textbook is mandatory: all the material (slides, source code, exercises, past exam examples) will be made available after each lecture on Virtuale.
Suggested introductory level textbook:
John V. Guttag. Introduction to Computation and Programming Using Python. Third Edition: With Application to Computational Modeling and Understanding Data. MIT Press, 2021. https://mitpress.mit.edu/books/introduction-computation-and-programming-using-python-third-edition
Other, very elementary-level, textbooks
Allen B. Downey. Think Python 2e. O'Reilly Media, 2012. ISBN 978-1449330729. Online manuscript: https://greenteapress.com/wp/think-python-2e/
Jessen Havill. Discovering Computer Science: Interdisciplinary Problems, Principles, and Python Programming. Chapman and Hall/CRC. ISBN 9781482254143
Reference books
Mark Lutz. Learning Python 5e. O'Reilly Media, 2013 [For Python, not for learning programming from scratch]
M. Gabbrielli, S. Martini. Programming Languages: Principles and Paradigms (2nd ed). Springer, 2023. [To learn how programming languages work.]
Module 2
Dirk van Dalen. Logic and structure. 4th edition, Springer.
K. Doets. From Logic to Logic Programming. The Mit Press.
Russell, Norvig. Artificial Intelligence: A Modern Approach (any edition). Pearson.

Codice insegnamento B5727

LANGUAGES AND ALGORITHMS FOR ARTIFICIAL INTELLIGENCE I.C. 1° anno · 2° semestre · 0 file

At the end of the course, the student has an understanding of the main linguistic techniques used in the context of AI, including the main aspects related to functional, logic and constraint programming.

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student has an understanding of the main linguistic techniques used in the context of AI, including the main aspects related to functional, logic and constraint programming.

Programma

Macchine astratte. La macchina Python. Programmazione in Python: nomi e loro visibilità, funzioni, oggetti modificabili e non modificabili, tipi di dato (numeri, stringhe, ennuple, liste, dizionari) e loro uso nella risoluzione di problemi di media difficoltà. Classi e oggetti; metodi ed ereditarietà. Eccezioni. La libreria NumPy e i suoi array N-dimensionali.
Modulo 2
Introduzione alla logica matematica. Unificazione. Risoluzione. Introduzione alla programmazione logica. I linguaggi Prolog. Programmazione logica con vincoli e programmazione concorrente con vincoli. Programmazione con vincoli. Il linguaggio MiniZinc.

Modalità d'esame

Il corso (Introduction to Languages for Artificial Intelligence) è parte del corso integrato “Languages and Algorithms for Artificial Intelligence”. Per avere un voto registrato sul libretto è necessario superare
Modulo 1 (Prof. Lodi): idoneità (pass/fail)
Modulo 2 (Prof. Gabbrielli): voto in trentesimi, superato con almeno 18/30.
Corso “Introduction to Computability and Complexity” con il Prof. Dal Lago: voto in trentesimi, superato con almeno 18/30.
Le tre prove possono essere sostenute in qualsiasi ordine e i voti positivi rimangono sempre validi.
Il voto finale si ottiene come media aritmetica dei voti nel Modulo 2 e nel Corso “Introduction to Computability and Complexity” , arrotondata all’intero più vicino.
Per ogni modulo sono previsti quattro appelli per ogni anno accademico.
Il modulo 1 sarà valutato attraverso un test di programmazione in Python della durata di 2 ore, con correzione automatica su casi di test, sulla piattaforma EOL. Il test valuterà la capacità degli studenti di risolvere correttamente semplici problemi di programmazione procedurale utilizzando Python (e la libreria NumPy).
Il sistema assegnerà un punteggio a ciascun caso di test per ogni esercizio. Il raggiungimento di un punteggio pari o superiore a 18/30 risulterà in un "pass", mentre un punteggio inferiore a 18/30 risulterà in un "fail" (il punteggio numerico non viene registrato).
Il test si svolgerà nei laboratori dell'Università e gli studenti avranno accesso a un IDE e alla documentazione di Python e NumPy. Non sarà possibile accedere ad altri siti web o a materiale cartaceo.
Un test preliminare potrebbe essere offerto a fine ottobre/inizio novembre. Gli altri appelli saranno in inverno, estate e autunno.
Seguire le lezioni è fondamentale per comprendere i concetti teorici. Per coloro che non possono partecipare, saranno disponibili le registrazioni. Per l'allenamento personale sono previsti diversi esercizi che non contribuiscono al voto. Lo svolgimento degli esercizi assegnati ogni settimana su Virtuale è fondamentale per l'apprendimento delle competenze di programmazione richieste. La valutazione automatica su casi di prova è un primo aiuto importante. I tutor e l'istruttore principale sono inoltre disponibili per chiarimenti.
Il modulo 2 sarà valutato mediante un esame scritto consistente in 2 esercizi sulle varie parti del corso da svolgersi in due ore. Seguire le lezssioni è importnate per prendere pratica anche con gli esercizi d'esame.

Testi di riferimento

Modulo 1
Nessun libro di testo è obbligatorio: tutto il materiale (diapositive, codice sorgente, esercizi, esempi di esami passati) sarà reso disponibile dopo ogni lezione su Virtuale.
Libro di testo suggerito (livello introduttivo)
John V. Guttag. Introduction to Computation and Programming Using Python. Third Edition: With Application to Computational Modeling and Understanding Data. MIT Press, 2021. https://mitpress.mit.edu/books/introduction-computation-and-programming-using-python-third-edition [Esiste anche la versione italiana]
Altri libri di testo di livello molto elementare
Allen B. Downey. Think Python 2e. O'Reilly Media, 2012. ISBN 978-1449330729. Disponibile online: https://greenteapress.com/wp/think-python-2e/
Jessen Havill. Discovering Computer Science: Interdisciplinary Problems, Principles, and Python Programming. Chapman and Hall/CRC. ISBN 9781482254143
Libri di consultazione
Mark Lutz. Learning Python 5e. O'Reilly Media, 2013 [Per Python, non per imparare la programmazione da zero].
M. Gabbrielli, S. Martini. Programming Languages: Principles and Paradigms (2nd ed). Springer, 2023. [Per imparare come funzionano i linguaggi di programmazione. Esiste anche la versione italiana.].
Modulo 2
Dirk van Dalen. Logic and structure. 4th edition, Springer.
K. Doets. From Logic to Logic Programming. The Mit Press.
Russell, Norvig. Artificial Intelligence: A Modern Approach (any edition). Pearson.

Codice insegnamento B5726

MACHINE LEARNING AND DATA MINING 1° anno · 1° semestre · 6 CFU · ING-INF/05 · 0 file

At the end of the course the student knows and understands: - the motivation and the components of the Data Mining process; - the general concepts, technologies and methodologies of Data Warehouse, OLAP and Data Lake, as…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course the student knows and understands: - the motivation and the components of the Data Mining process; - the general concepts, technologies and methodologies of Data Warehouse, OLAP and Data Lake, as enabling factors of the Data Mining process; - the principles and the most relevant use cases of a wide set of Machine Learning algorithms which are used to extract relevant and actionable information from large amounts of data. At the end of the course the student is able to: - design the main steps of a Data Mining process - choose the Machine Learning methods best suited for the process - evaluate the quality of the result in order to support strategic and operational decisions.

Programma

Part 1 - Data Mining
Introduction to the Data Mining Process Architectures of systems with data mining components Enterprise Data Warehouse Data Lake Case studies
Part 2 - Machine Learning
What is Machine Learning: some history and motivating examples Theory of learning Supervised vs unsupervised learning Classification and regression Model Selection, validation and presentation of results Regression Classification with linear discrimination, decision trees, Bayesian inference, Support Vector Machines, k-nearest neighbors, logistic regression, random forests, adaboost Ensemble learning, boosting, bagging Association rules and the Apriori algorithm Clustering/segmentation with k-means, dbscan, Expectation Maximization, hierarchical methods, kernel methods Analysis of case studies CRISP-DM methodology
Pre-requisites
Fundamentals of programming Fundamentals of calculus and linear algebra Fundamentals of statistics and probabilities Useful some general notion on Data Base Management Systems

Modalità d'esame

The Verification of knowledge is tested through multiple choice questions. The minimum to pass is to answer correctly half + 1 of the questions. The weight of this part is 33%.
The Verification of abilities will be tested in lab with the development of a program for the execution of a Machine Learning task on an assigned data set. The quality of the solution will be evaluated on the basis of the correctness of the approach, the correctness of the solution, the quality of the coding and of the documentation. The minimum to pass is to give a sensible approach and a reasonable coding. The weight of this part is 67%
It is also possible, on request, to have an oral examination, with possible outcomes between -3="no answer" and +3="correct answer", to be added to the weighted sum of the above-mentioned scores.
Additional details on Assessment are available in the course page on https://virtuale.unibo.it [https://virtuale.unibo.it/]
For the students of Machine Learning and Deep Learning (i.c.) the registration will be executed only after passing the Deep Learning module.

Testi di riferimento

Introduction to machine learning / Ethem Alpaydin. - 3. ed. - Cambridge : The MIT Press, 2014. - XXII, 613 p. - link to the online version [https://ebookcentral.proquest.com/lib/unibo/detail.action?docID=3339851] Scikit-Learn [https://scikit-learn.org/stable/documentation.html ], or Python Data Science Handbook [https://jakevdp.github.io/PythonDataScienceHandbook/]
Shearer C., The CRISP-DM model: the new blueprint for data mining, J Data Warehousing (2000); 5:13—22.

Codice insegnamento 95631

MACHINE LEARNING AND DEEP LEARNING I.C. 1° anno · 2° semestre · 0 file

At the end of the course the student knows and understands: - the motivation and the components of the Data Mining process; - the general concepts, technologies and methodologies of Data Warehouse, OLAP and Data Lake, as…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course the student knows and understands: - the motivation and the components of the Data Mining process; - the general concepts, technologies and methodologies of Data Warehouse, OLAP and Data Lake, as enabling factors of the Data Mining process; - the principles and the most relevant use cases of a wide set of Machine Learning algorithms which are used to extract relevant and actionable information from large amounts of data. At the end of the course the student is able to: - design the main steps of a Data Mining process - choose the Machine Learning methods best suited for the process - evaluate the quality of the result in order to support strategic and operational decisions.

Programma

Il corso e' tenuto in lingua inglese. Per i contenuti e le altre informazioni sul corso si faccia riferimento alla versione inglese.

Codice insegnamento B2127

STATISTICAL AND MATHEMATICAL METHODS FOR ARTIFICIAL INTELLIGENCE 1° anno · 1° semestre · 6 CFU · SECS-S/01 · 0 file

At the end of the course, the student masters the basic mathematical and statistical methods needed to acquire skills in artificial intelligence foundations, theories and applications.

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student masters the basic mathematical and statistical methods needed to acquire skills in artificial intelligence foundations, theories and applications.

Programma

The course is organised into four modules. It introduces the mathematical and statistical tools required to analyse multivariate data, quantify uncertainty and construct predictive models. Theoretical concepts are accompanied by exercises, numerical examples and applications using R.
Module 1 – Basics of Linear Algebra
Vectors and matrices: notation and basic operations Matrix multiplication and transposition Systems of linear equations Matrix inverse, determinant and trace Vector norms, distances and angles Linear combinations, span and linear independence Eigenvalues and eigenvectors Spectral decomposition of symmetric matrices Orthogonal projections and positive semi-definite matrices Quadratic forms and basic optimisation concepts
Module 2 – Principal Component Analysis
Multivariate data and data matrices Centring and standardisation of variables Sample variance, covariance and correlation Covariance and correlation matrices Geometric interpretation of principal components Principal directions, loadings and scores Spectral decomposition of the covariance matrix Singular value decomposition Explained variance and selection of the number of components Graphical representations and interpretation of PCA results Projection onto a lower-dimensional space Low-rank reconstruction of the original data Implementation and interpretation of PCA in R
Module 3 – Introduction to Statistics
Populations, samples and random sampling Events, probability rules and conditional probability Independence, partitions and Bayes’ theorem Random variables, probability mass functions, density functions and cumulative distribution functions Expectation, variance, covariance and correlation Quantiles and transformations of random variables Bernoulli, binomial, uniform, exponential and Gaussian distributions Multivariate random variables and the multivariate Gaussian distribution Empirical distributions and descriptive statistics Parameters, estimators and observed estimates Plug-in estimation and maximum likelihood estimation Properties of estimators: bias, variance, mean squared error and consistency Sampling distributions and asymptotic normality Monte Carlo simulation and evaluation of statistical procedures Exact, asymptotic and bootstrap confidence intervals
Module 4 – Regression Models
Statistical relationships between variables Simple and multiple linear regression The linear regression model and its assumptions Least-squares estimation Matrix formulation of linear regression Interpretation of regression coefficients Fitted values, residuals and goodness of fit Statistical inference for regression coefficients Confidence intervals and prediction intervals Residual analysis and graphical diagnostics Leverage, influential observations and Cook’s distance Training error, test error and model assessment Cross-validation The bias–variance trade-off Model selection Regularised regression: ridge regression and lasso Fitting, evaluating and interpreting regression models in R

Modalità d'esame

Assessment is based on written, closed-book examinations. The use of books, notes or other supporting materials is not permitted. The questions and exercises are similar in type and level of difficulty to those discussed and solved during the course.
The final grade may be obtained by taking the written examination at the end of the semester or during either of the two subsequent resit sessions.
Students who wish to do so may replace the end-of-semester examination with continuous assessment based on the weekly tests taken during the semester. To select this option, students must submit a request in advance, towards the end of the course. The continuous-assessment grade is calculated as the average of the weekly test results, after excluding the single lowest result. A test missed because of absence is assigned a grade of zero before the lowest result is excluded.

Testi di riferimento

The class material is partly based on the book:
Deisenroth, M. P., Faisal, A. A., and Ong, C. S. (2020). Mathematics for Machine Learning. Cambridge University Press. ISBN: 978-1-108-45514-5.
The book is freely available online at: https://mml-book.github.io/book/mml-book.pdf

Codice insegnamento 91255

AGENTIC AI SYSTEMS M 2° anno · 2° semestre · 8 CFU · ING-INF/05 · 0 file

At the end of this course, the student will have a solid understanding of the state of the art and the key conceptual and practical aspects of the design, implementation, and evaluation of agentic AI systems. These are…

Scheda dell'insegnamento

Obiettivi formativi

At the end of this course, the student will have a solid understanding of the state of the art and the key conceptual and practical aspects of the design, implementation, and evaluation of agentic AI systems. These are systems that can act autonomously, make decisions, and effectively interact with their environment to achieve goals. The student will gain in-depth knowledge of the latest advancements in agentic AI, including current research trends and emerging technologies, and develop practical skills and hands-on experience in designing such systems. The course will equip the student with the ability to critically assess the ethical, societal, and philosophical implications of these technologies, providing an interdisciplinary perspective to the field.

Programma

Prerequisites
There are no formal prerequisites. However, there is an expectation that students will have an in-depth knowledge of Machine Learning (including Deep Learning).
In addition, students should have a working knowledge of a deep learning framework, such as PyTorch or JAX.
Syllabus
Introduction to the design of agentic AI systems: analysis of the current technological and geopolitical scenario, and general definitions.
Introduction to Reinforcement Learning (RL): multi-armed bandits, Montecarlo methods, tabular methods, function approximation methods, and policy approximation methods.
Applications of RL to games, classic control theory problems, and robotics.
Introduction to algorithmic game theory for multi-agent learning systems: cooperation and coordination, social dilemmas, and Multi-Agent Reinforcement Learning.
Agents based on large language models/foundational models: pre-training, post-training using Reinforcement Learning from human-feedback (RLHF), Direct Preference Optimization (DPO), Reinforcement Learning from Verifiable Rewards (RLVR), and reasoning models.
Intelligent machines that create: Generative Learning, agentic AI systems & AI creativity.
Open problems and the future: safety, value alignment, super-intelligence, controllability, and self-awareness. Ethical and philosophical implications of agentic AI systems.

Modalità d'esame

Oral or written exam on the theoretical aspects of the course (70%), with a compulsory research project to be submitted before the exam (30%), and class participation (bonus of up to 2 points). Students will be invited to read papers about the state-of-the-art in agentic AI systems. The papers will be discussed during the lectures. The project will include the design, implementation and evaluation of an AI algorithm/system (related to the topics of the module) and a written report with a structure similar to a research paper. The project will have to be submitted before the closing date for the registration to the exam on AlmaEsami. The topic(s) of the project will be given by the instructors of the module (i.e., it is not an "open" research problem). Instructions for the submission of the project will be given during the module. The registration to the exam through AlmaEsami is compulsory.

Testi di riferimento

During the course, the instructor will provide an extensive list of pointers (scientific papers, technical documentation, books, etc.) for each topic.
Useful textbooks for the course include the following:
Christopher M. Bishop and Hugh Bishop. Deep Learning: Foundations and Concepts. Springer. 2023. Dario Floreano and Claudio Mattiussi. Bio-inspired Artificial Intelligence: Theories, Methods and Technologies. MIT Press. 2008. David Foster. Generative Deep Learning: Teaching Machines to Paint, Write, Compose and Play. Second Edition. O’Reilly. 2023. Peter Norvig and Stuart J. Russell. Artificial Intelligence: A Modern Approach. Fourth Edition. Pearson. 2020. Max Pumperla and Kevin Ferguson. Deep Learning and the Game of Go. Manning. 2019. Richard R. Sutton and Andrew G. Barto. Reinforcement Learning: An Introduction. MIT Press 2018.

Codice insegnamento B8565

Architecture and Platforms for Artificial Intelligence 2° anno · 1° semestre · 6 CFU · INF/01 · 0 file

At the end of the course, the student has a deep understanding of the requirements of machine-learning workloads for computing systems, has an understanding of the main architectures for accelerating machine learning…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student has a deep understanding of the requirements of machine-learning workloads for computing systems, has an understanding of the main architectures for accelerating machine learning workloads and heterogeneous architectures for embedded machine learning, and of the most popular platforms made available by cloud providers to specifically support machine/deep learning applications.

Programma

Module 1:
Introduction to parallel programming. Parallel programming patterns: embarrassingly parallel, decomposition, master/worker, scan, reduce. Shared-Memory programming with OpenMP. OpenMP programming model: the “omp parallel” construct, scoping constructs and other work-sharing constructs. GPU programming with CUDA. CUDA architecture and memory hierarchy. The CUDA programming model: threads, groups, grid. Synchronization primitives and shared memory.
Prerequisites for module 1: good knowledge of C programming in the Unix/Linux environment, and basic understanding of computer architectures and concurrency theory.
Module 2:
From ML to DNNs - a computational perspective
Introduction to key computational kernels (dot-product, matrix multiply...). Inference vs training - workload analysis characterization. The NN computational zoo: DNNs, CNNs, RNNs, Attention-based Networks, State Based networks.
Running ML workloads on programmable processors
recap of processor instruction set architecture (ISA) with focus on data processing. improving processor ISAs for ML: RISC-V and ARM use cases. fundamentals of parallel processor architecture and parallelization of ML workloads.
Algorithmic optimizations for ML
Key bottlenecks taxonomy of optimization techniques. Algorithmic techniques (e.g. Strassen, Winograd, FFT). Model distillation: efficient NN models - depthwise convolutions, inverse bottleneck, optimized attention, introduction to Neural Architectural Search. Quantization and sparsity: scalar, block, vector.
Prerequisites for module 2: Programming in C, basic computer architecture concepts, basics linear algebra and vector calculu.

Modalità d'esame

The exam consists of two parts which are independent and can be done in any orde. However, the exams of both modules must be completed on the same academic year (partial grades are lost at the end of the academic year). Important note: to get the final grade you must pass the exams for both modules 1 and 2, i.e., it is not possible to register partial grades.
Module 1: Project work, which consists of the design and implementation of a parallel program and a written report. The project work must be done individually by each student; collaboration is not allowed. The program must implement a parallel algorithm according to specifications provided by the instructor, using C/OpenMP and/or CUDA/C. No other programming languages are allowed. The report has a maximum length of 6 pages, and must describe and motivate the parallelization strategies adopted, and analyze the performance of the parallel program. The instructor may require a brief oral discussion of the project.
Module 2: Written exam with oral discussion: the written exam is compulsory and consists of solving problems and answering questions. The oral exam is optional and consists of in-depth questions on topics covered in class.
Final grade: To get a final grade it is necessary to pass the exams for both modules with a passing mark, i.e., at least 18 out of 30; the final grade is computed as the average of the grades of the two modules, rounded to the nearest integer. Honors (“lode”) will be awarded for results of very high quality at the discretion of the instructors.

Testi di riferimento

Suggested readings for Module 1: selected parts from the following books:
Peter Pacheco, Matthew Malensek, An Introduction to Parallel Programming [https://shop.elsevier.com/books/an-introduction-to-parallel-programming/pacheco/978-0-12-804605-0], 2nd ed., Morgan Kaufmann, 2021, ISBN 9780128046050.
CUDA C programming guide, NVidia Corporation, freely available at http://docs.nvidia.com/cuda/cuda-c-programming-guide/
Suggested readings for Module 2: selected parts from the following books:
Dive into Deep Learning (online: d2l.ai).
Efficient Processing of Deep Neural Networks (online: https://link.springer.com/book/10.1007/978-3-031-01766-7 ).
Machine Learning Systems (online: mlsysbook.ai).

Codice insegnamento 91259

Artificial Intelligence and Robotics 2° anno · 2° semestre · 6 CFU · ING-INF/05 · 0 file
Artificial Intelligence for Medicine M 2° anno · 2° semestre · 6 CFU · ING-INF/06 · 0 file

At the end of the course, the student has: -knowledge regarding the need for AI in Medicine; -understanding of weaknesses of AI techniques, methods to overcome the challenges of AI in Medicine, and ways in which AI may…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student has: -knowledge regarding the need for AI in Medicine; -understanding of weaknesses of AI techniques, methods to overcome the challenges of AI in Medicine, and ways in which AI may improve healthcare; -essential knowledge to develop and implement reliable AI solutions in clinical research (using, e.g., supervised and unsupervised machine and deep learning techniques, explainable AI methods, and generative adversarial techniques); -practical skills to develop state-of-the-art AI tools with real-world medical data (e.g., clinical and imaging data); -the ability to critically read, discuss and evaluate methods and results of studies using AI in Medicine; -an overview of state-of-the-art AI-powered tools in Medicine.

Programma

· Introduction to AI in Health and Medicine: progress, challenges, and opportunities; · Introduction to Clinical Data: medical data collection and management, quality control, data harmonization, data augmentation, synthetic datasets, dataset size vs. confidence intervals; · Fundamentals of AI for Medicine: Introduction to machine learning. Taxonomy of machine learning algorithms. Introduction to Github and Google Colab for collaborative development and cloud-based execution. Model capacity, generalization, and regularization techniques. Hyperparameter tuning. Validation schemas: hold-out, cross-validation, nested hold-out, nested cross-validation, leave-one-out, and stratified sampling. Introduction to Python programming. Practical case study: age prediction task using brain Magnetic Resonance data. Weaknesses of AI techniques and their consequences in Medicine, evaluation of AI tools in Medicine, explainable AI, AI reproducibility, beyond supervised learning, federated and swarm learning, transparent reporting, clinical integration; · Hands-on Projects with Clinical Data: projects to provide technical experience in AI for Medicine; · Real-world AI-powered tools of AI in Medicine: an overview of state-of-the-art AI solutions in Medicine and Healthcare.

Modalità d'esame

The learning assessment will be performed through a final examination consisting of an oral test focused on both the theoretical concepts presented during the lessons and the software tools used in the laboratory. The exam aims to ascertain the student’s theoretical-practical skills and competences, the correctness of language, and the clarity of concepts and exposition.
As part of the final assessment, students are required to develop and present a software project using Python in Google Colab, applying artificial intelligence to solve a real-world biological or medical problem. The project may be selected from a list provided during the course or proposed independently by the student, subject to instructor approval. Projects may be completed individually or in pairs; in the latter case, the scope and complexity of the project must be appropriately increased.
The code must be implemented in Python and must run in Google Colab. It must be submitted as a .ipynb notebook. Students may submit their notebook in one of the following ways:
via a personal GitHub repository (provide the link), via a Google Colab shareable link, or by sending the file directly via email to the instructor.
In addition to the code, students must submit a project report in PDF format, prepared according to the official template available in the course’s GitHub repository or on the Virtuale platform.
Both the code and the report must be submitted at least 7 days before the scheduled exam date.
Students with Specific Learning Disabilities (SLD) or temporary/permanent disabilities are strongly encouraged to contact the University Office in charge in a timely manner (https://site.unibo.it/studenti-con-disabilita-e-dsa/en ). The office will be responsible for proposing any necessary accommodations to the students concerned. These accommodations must be submitted to the course instructor at least 15 days in advance for approval, who will assess their appropriateness in relation to the learning objectives of the course.

Testi di riferimento

Notes provided by the Professor.
M. Lutz, "Learning Python", O'Reilly, 2013
I. Goodfellow, Y. Bengio, A. Courville, "Deep Learning", MIT Press, 2016 (https://www.deeplearningbook.org/ )

Codice insegnamento B5224

Artificial Intelligence in Industry 2° anno · 1° semestre · 6 CFU · ING-INF/05 · 0 file

At the end of the course, the student has a deep knowledge of industrial applications that benefit from the use of machine learning, optimization and simulation. The student has a domain-specific knowledge of practical…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student has a deep knowledge of industrial applications that benefit from the use of machine learning, optimization and simulation. The student has a domain-specific knowledge of practical use cases discussed in collaboration with industrial experts in a variety of domains such as manufacturing, automotive and multi-media.

Programma

The course is primarily delivered as a series of simplified industrial use cases. The goal is provide examples of challenges that typically arise when solving industrial use cases, and to develop critical thinking and problem solving skils.
Use cases may cover topics such as:
Anomaly detection Remaining Useful Life (RUL) estimation RUL based maintenance policies Resource management planning Recommendation systems with fairness constraints Power network management problems Epidemic control Production planning
The course will emphasize the ability to view problems in their entirety and adapt to their peculiarities. This will frequently require to combine heterogeneous solution techniques, using integration schemes both simple and advanced.
The employed method will include:
Mathematical modeling of industrial problems Predictive and diagnostic models for time series Combinatorial Optimization Integration methods for Probabilistic Models and Machine Learning Integration methods for constraints and Machine Learning Integration methods for combinatorial optimization and Machine Learning
The course will include seminars on real-world use cases, from industry experts.
The course contents may (and typically will) be subject to changes, so as to adapt to some degree to the interests and characteristics of the attending students.

Modalità d'esame

Individual or group projects (one to three students).
Students may freely propose a project topic, or pick from a list that will be published roughly midway through the course.
In both cases, the details of the course project must be discussed with the teacher before activities begin.
The exam will consist in the presentation and discussion of the project work. The evaluation:
Will not take into account the outcome of the project (meaning that negative results are considered fine) It will instead focus on the quality of the method, with emphasis on: 1) motivation for all the choices that have been made; 2) interpretation of the results; 3) awareness of the capabilities and limits of the tools that have been used
The use of generative AI tools in the preparation of the project is permitted; however, the student is considered the author of the entire submission. This requires the ability to understand and justify the methods, code, and results. Should this capability prove inadequate, up to 10 points may be deducted from the final grade.

Testi di riferimento

The main teaching material will consists of mostly of interactive notebooks developed using the Jupyter system, which will contain pointers to relevant references.

Codice insegnamento 91261

Big Data Analytics and Text Mining 2° anno · 1° semestre · 6 CFU · ING-INF/05 · 0 file

At the end of the course, the student understands how corpora and big data sets can be analyzed to derive strategic knowledge and data-driven decisions. The student is able to address the main data and text analytics…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student understands how corpora and big data sets can be analyzed to derive strategic knowledge and data-driven decisions. The student is able to address the main data and text analytics tasks such as data selection, transformation, analysis and interpretation, moreover is able to leverage deep learning pipelines and advanced solutions for text mining and natural language understanding downstream goals.

Programma

Module 1 - Text Mining and Large Language Models (Prof. Gianluca Moro)
The module will begin on September 21, 2026, and focuses on the following state-of-the-art deep learning advancements to cope with challenging and highly business demanded natural language processing and understanding tasks with core open source technologies
(see the virtuale space of the course and our GitHub repo)
Neural Language Modeling Foundations Transformer Architecture, Pre-Training and Fine-Tuning Techniques, Decoding Strategies, Evaluation (Natural Language Generation Metrics, LLM-as-a-judge). Large Language Models Scaling Laws, Prompting vs Fine-Tuning, Instruction Fine-Tuning, Preference Alignment, Efficient Attention Mechanisms (e.g., BigBird, Performer, Key-Value Caching, Multi-Query Attention) Compression and Quantization Methods (GPTQ, AWQ, GGUF), Parameter-Efficient Fine-Tuning (e.g., LoRA, QLoRA, GaLoRE, Prompt Tuning), Mixture-of-Experts, Vision-Language Models.
Knowledge-Enhanced Natural Language Processing. Retrieval-Augmented Generation (Chunking Strategies, Architectures) and VectorDBs, Agents and Tool Calling (Large Action Models - LAM), Graph Neural Networks, Graph Injection into Language Models for Trustworthiness.
Labs on real-world case studies and in enterprise settings with core technologies Python, Pytorch, HuggingFace, LlamaIndex: -- Prompting vs Full Fine-Tuning vs Parameter-Efficient Fine-Tuning for Dialogue Summarization; Foundational Multimodal Large Language Models for Visual Question Answering. -- Efficient, Retrieval-Augmented Conversational Agents for Qustion-Answering in the Legal Domain. -- Graph Learning, Embedding and Injection into Language Models for Semantics-Aware Lay Summarization; GraphRAG and Structured Query Generation to Interact with DBMS and Knowledge Graphs in Multi-Source Question Answering; -- Graph Verbalization into Large Language Model Prompts for Medical Question Answering.
The module introduces also new published SOTA results in top-tier AI conferences for research and industrial projects, we also achieved on some of these topics.
Module 2 - Big Data Analytics (Prof. Stefano Lodi)
Data Mining in Big Data Environments Maps and reductions in parallel programming. The MapReduce programming model. The Hadoop implementation of MapReduce. The Python API to the Spark system and examples of parallel programs. The Machine Learning Library (MLlib) of Spark.

Modalità d'esame

The exam of the course consists of an unique multiple-choice test for both modules and the (online) discussion of an individual or group small project, chosen with a teacher, on one module. The project can be joined with the 3 CFU project of B3157 - PROJECT WORK IN BIG DATA ANALYTICS AND TEXT MINING but also with master theses, internships and other courses Multiple-choice test sits: at the end of the lessons before Christmas, plus in Jan and Feb.
If needed the student can receive the assistance of the tutor for the development of the project. The project's scope should be approximately equivalent to that of a lab of the course and should take about a couple of weeks of work
A non-exhaustive list of dataset and text sets for the project is available in the "virtuale" teaching resources, but the students can also propose to use a different data set.

Testi di riferimento

Readings/Bibliography
Module 1 - Text Mining and Large Language Models (Prof. Gianluca Moro)
Readings: Slides, lab notebooks, datasets and recent papers will be supplied by the teacher, also from our repo
Suggested readings: Natural Language Processing Recipes Unlocking Text Data with Machine Learning and Deep Learning using Python, Akshay Kulkarni and Adarsha Shivananda, 2024
Module 2 - Big Data Analytics (Prof. Stefano Lodi)
White, T. (2009). Hadoop: The definitive guide 4th Edition. Reilly Media. Chambers, B., & Zaharia, M. (2018). Spark: The definitive guide: Big data processing made simple. Reilly Media, Inc.

Codice insegnamento B2133

Blockchain and Cryptocurrencies 2° anno · 1° semestre · 6 CFU · INF/01 · 0 file

At the end of the course, the student knows the relevant themes related to blockchain technologies, cryptocurrencies, smart contracts and novel applications that can be built over the blockchain. The student is able to…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student knows the relevant themes related to blockchain technologies, cryptocurrencies, smart contracts and novel applications that can be built over the blockchain. The student is able to develop simple smart contracts that can be deployed on a blockchain.

Programma

Bitcoin and novel cryptocurrencies gathered momentum in the last months. More and more investors look with interest at these technologies, while others label them as a dangerous speculative bubble. The truth is that the blockchain, and the alternative implementations of a distributed ledger, represent very interesting technologies, that can be exploited to build novel distributed applications. The underlying building blocks are related to many concepts and research areas of computer science in general. This course will illustrate the main principles and conceptual foundations of the blockchain and the Bitcoin network.
Program
Introduction to peer-to-peer sysystems Overlay topologies and decentralization Introduction to Crypto and Cryptocurrencies The blockchain: how to achieve decentralization Transactions and transaction scripting languages Mining Attacks to the blockchain Anonymity Smart contracts

Modalità d'esame

Project
Students with SLD (Specific Learning Disorders) or temporary/permanent disabilities: you are strongly advised to contact the relevant University office in a timely manner (). The office will propose any necessary accommodations to the students concerned. These accommodations must be submitted at least 15 days in advance for approval by the instructor, who will assess their suitability also in relation to the learning objectives of the course.

Testi di riferimento

Lecture notes and slides will be provided by the instructor, along with papers and a list of bibliographical references and additional material. All the course material is in English.

Codice insegnamento 90748

Computational Ethics 2° anno · 2° semestre · 4 CFU · IUS/20 · 0 file

Alla fine del corso, lo studente conosce le principali questioni metaetiche, i modelli etici normativi e i contributi teorici delle scienze cognitive legati alla traducibilità in termini computazionali dei giudizi…

Scheda dell'insegnamento

Scheda dell'a.a. 2025/2026: quella dell'anno in corso non è ancora pubblicata.

Obiettivi formativi

Alla fine del corso, lo studente conosce le principali questioni metaetiche, i modelli etici normativi e i contributi teorici delle scienze cognitive legati alla traducibilità in termini computazionali dei giudizi morali. Alla fine del corso, lo studente è capace di ragionare criticamente sulle proposte teoriche alternative di formulazione algoritmica dell’etica, nonché sulle teorie che negano la possibilità dell’etica computazionale.

Programma

Il contenuto dettagliato del corso corrisponde all’elenco delle letture e dei materiali discussi durante le lezioni, comprese eventuali attività pratiche o di laboratorio. Il corso affronta le principali questioni etiche e giuridiche legate all’intelligenza artificiale, includendo un’introduzione all’Etica dell’IA, alla Machine Ethics e all’Etica Computazionale, nonché l’analisi delle loro relazioni con il diritto. Sono inoltre previste discussioni e analisi di casi di studio su processi decisionali algoritmici, IA e discriminazione, protezione dei dati, manipolazione, equità e trasparenza. Il corso è progettato per studenti che non abbiano una precedente formazione in etica o filosofia. È consigliata una formazione di base in informatica.

Modalità d'esame

L’esame consisterà in una prova orale composta da tre domande sugli argomenti del corso. Particolare importanza sarà attribuita a una tesina. Le indicazioni dettagliate relative alla tesina (argomento, modalità di svolgimento e criteri di valutazione) saranno fornite durante il corso.

Testi di riferimento

I materiali didattici saranno resi disponibili su Virtuale.

Codice insegnamento B0708

Cryptography 2° anno · 1° semestre · 6 CFU · INF/01 · 0 file

At the end of the course, the student knows the basics of modern cryptography and some techniques for the analysis of security protocols. He or she can verify the absence of security bugs on simple protocols.

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student knows the basics of modern cryptography and some techniques for the analysis of security protocols. He or she can verify the absence of security bugs on simple protocols.

Programma

This course deals with some fundamental notions on modern cryptography and some techniques for the formal verification of cryptographic protocols. In addition to many new concepts, we discuss some cryptographic techniques already seen in previous courses, studying the most interesting properties . The main emphasis of this course is on the theoretical aspects of cryptography: it attempts to give a clear and accurate account on security, in order to give students the tools to assess (and not just to use) cryptographic techniques . In other words, we focus a lot on the "why" maybe putting the "how" behind the scenes. More specifically, we seek to answer questions such as the following: when a cryptographic technique can be consider safe? Is it possible to formally prove that a cryptographic technique is secure ? Is it possible to analyze the security of a cryptographic protocol in an automatic or semi-automatic way?
Topics covered include perfect security, pseudorandomness, public and private key ciphers, and the symbolic model.

Modalità d'esame

There is a single examination format: an oral examination covering the entire course syllabus, preceded by a very brief written test consisting of five multiple-choice questions. The written test does not contribute to the final grade; its sole purpose is to verify that students possess the basic knowledge required to take the oral examination.

Testi di riferimento

[1] J. Katz and Y. Lindell. Introduction to Modern Cryptography. Chapman & Hall, 2007. [2] O. Goldreich. Foundations of Cryptography I: Basic Tools. Cambridge University Press, 2001. [3] O. Goldreich. Foundations of Cryptography II: Basic Applications. Cambridge University Press, 2004. [4] D. R. Stinson. Cryptography: theory and practice. Chapman & Hall, Third Edition, 2006. [5] J. A. Buchmann. Introduction to Cryptography. Springer, Second Edition, 2004. [6] M. Abadi. Security Protocols: Principles and Calculi. Foundations of Security Analysis and Design IV, FOSAD 2006/2007 Tutorial Lectures, Springer-Verlag (2007), 1-23. [7] M. Abadi and P. Rogaway. Reconciling Two Views of Cryptography. Journal of Cryptology 15(2), 103-127 (2002). [8] B. Blanchet. An Efficient Cryptographic Protocol Verifier Based on Prolog Rules. 14th IEEE Computer Security Foundations Workshop (CSFW-14), pages 82-96, Cape Breton, Nova Scotia, Canada, June 2001. IEEE Computer Society. [9] B. Blanchet. ProVerif. Automatic Cryptographic Protocol Verifier. User Manual.

Codice insegnamento 93467

Cybersecurity 2° anno · 1° semestre · 6 CFU · INF/01 · 0 file

The student will learn: historical perspective and motivations for cyber-security, principles of data security, principles of software security, component and connection security, network security.

Scheda dell'insegnamento

Obiettivi formativi

The student will learn: historical perspective and motivations for cyber-security, principles of data security, principles of software security, component and connection security, network security.

Programma

Cyber scenario Cybersecurity goals: security and availability of information and services
Defensive and Offensive security
Analysis of cyber threats: actors and motivations (Too many) vulnerability human and technological issues A top-down approach to cybersecurity Cyber risk management Qualitative and quantitative evaluation Strategies, policies and technologies Assessment and validation Cyber threat intelligence Modern approaches: AI for cybersecurity, Zero Trust, Deception

Modalità d'esame

The students can choose between two alternatives. (1) Oral exam that includes the analysis of a networked system and its services, discussion about cybersecurity issues, presentation of possible solutions. (2) Project (max 3 students), presentation of the results and discussion. The students interested to the option (2) must agree on the topic of the group project with the teacher before the end of November 2025 and complete the assessment in the first exam session (by the end of February 2026).
The students interested to the option (1) can take the exam whenever they want.
For all students the positive evaluation will go from 18 to 30 (possibly, cum laude).

Testi di riferimento

Slides, teacher's notes, book chapters, scientific articles and online resources indicated on the course website (virtuale.unibo.it).

Codice insegnamento 93470

Distributed Autonomous Systems M 2° anno · 2° semestre · 6 CFU · ING-INF/04 · 0 file

The course focuses on the design of control, optimization and learning methods and software tools for teams of autonomous systems. These systems consist of cooperative agents, as intelligent robots, autonomous vehicles…

Scheda dell'insegnamento

Obiettivi formativi

The course focuses on the design of control, optimization and learning methods and software tools for teams of autonomous systems. These systems consist of cooperative agents, as intelligent robots, autonomous vehicles and decision systems, that aim at performing complex tasks according to a federated and distributed computing paradigm. At the end of the course students will know how to design selected distributed control, optimization and learning algorithms to solve complex tasks involving teams of autonomous systems. To bridge the gap between theory and application, laboratory activities will allow students to design software tools for the studied algorithms and apply them to a number of application domains, including, e.g., planning,guidance and optimal control of cooperative autonomous vehicles and intelligent robots as well as machine learning and data analytics for decision systems.

Programma

Introduction to Distributed Autonomous Systems New paradigms and application domains of autonomous systems: decision systems for data analytics (e.g., recommender systems and localization), sensor networks, cooperative robotics, cooperative mobility, smart energy systems. Introduction to distributed systems: centralized versus distributed computing, key properties and main goals for distributed systems. Modeling of distributed systems Models of distributed systems. Graph theory as a tool to model communication among network agents. Preliminaries on graph theory and examples. Distributed algorithms and distributed control laws. Introduction to Python programming for distributed computing and cooperative robotics via Robotic Operating System 2. Basic distributed algorithms Averaging protocols and linear consensus algorithms for multi-agent systems. Complex tasks (e.g., autonomous formation control, containment in leader-follower networks) based on linear consensus algorithms. Practical Python and ROS 2 implementation of averaging and distributed control laws on case study examples from decision and control networks. Introduction to distributed optimization Optimization basics. Main problem set-ups and examples from estimation, machine learning, decision making, and control in cyber-physical networks. Distributed decision making via consensus optimization Consensus optimization algorithms based on averaging. Distributed gradient and gradient tracking methods. Practical Python implementation on case studies from federated and distributed machine learning, e.g., logistic regression, support vector machine, training of neural networks for classification. Cooperative robotics via distributed optimization Distributed optimization setups and algorithms for robotic applications. Hierarchical robotic control architectures. Practical Python implementation on case study examples from formation control, collision avoidance, surveillance and task allocation in cooperative robotics. ROS 2 toolboxes for cooperative robotics.

Modalità d'esame

Oral exam and discussion of a course project.

Testi di riferimento

The course is based on the following references: F. Bullo, “Lectures on Network Systems”
G. Notarstefano, I. Notarnicola, A. Camisa, “Distributed Optimization for Cyber-Physical Networks”
A. Testa, G. Carnevale, G. Notarstefano, "A Tutorial on Distributed Optimization for Cooperative Robotics: from Setups and Algorithms to Toolboxes and Research Directions"
and on a set of slides which will be made available throughout the term.

Codice insegnamento 92995

Ethics in Artificial Intelligence 2° anno · 2° semestre · 6 CFU · IUS/20 · 0 file

Al termine dell'attività formativa, lo studente comprende i principali aspetti etici collegati alla creazione e all'uso di sistemi di intelligenza artificiale. Lo studente è capace di ragionare criticamente sui…

Scheda dell'insegnamento

Scheda dell'a.a. 2025/2026: quella dell'anno in corso non è ancora pubblicata.

Obiettivi formativi

Al termine dell'attività formativa, lo studente comprende i principali aspetti etici collegati alla creazione e all'uso di sistemi di intelligenza artificiale. Lo studente è capace di ragionare criticamente sui principali problemi di etica delle macchine collegati a sistemi AI dotati di capacità di decisione autonoma ed è capace di valutare l'impatto degli aspetti etici e legali dei sistemi di AI.

Programma

Il corso si propone di fornire una panoramica approfondita delle numerose questioni etiche e sociali sollevate dalle tecnologie dell'informazione e della comunicazione (ICT), con particolare attenzione all'Intelligenza Artificiale e al suo impatto sulla società e sugli individui. Gli studenti impareranno a conoscere le principali sfide sociali ed etiche poste dalle ICTs e come affrontarle in modo critico. L'analisi concettuale sarà supportata dalla discussione di casi di studio pratici. Gli studenti Erasmus seguono lo stesso programma degli studenti regolari. Contenuti del corso: Introduzione all'etica Tecnologie dell'informazione, comportamento mirato e intelligenza; Singolarità e superintelligenza; Agente artificiale, libero arbitrio, coscienza; Agenti artificiali e responsabilità; Etica delle macchine; Etica dell'IA e roboetica; Machine Learning, Big Data e problemi di bias e discriminazione; Antropomorfismo, Interazione Umano/Computer/Robot (HCI, HRI) e dignità umana; IA e fiducia; Human in the loop, Sicurezza e Responsabilità; Spiegabilità e trasparenza dell'intelligenza artificiale; Valutazione dei casi d'uso dell'IA. Scenari Socio-Tecnici Valutazione dei casi d'uso dell'IA. Tensioni etiche, Compensazioni. Possibili casi d'uso: Robot militari e sistemi d'arma autonomi; Veicoli a guida autonoma; Sistemi esperti: COMPAS, Watson; Aviazione e gestione del traffico aereo; AI e creatività artistica (TheNextRembrandt, Obvious Art, Shimon); Etica dell'AI nella sanità Rilevanza legale dell'etica dell'IA Ethical Business IA e privacy Modelli computabili di norme giuridiche ed etiche e del ragionamento (con esercizi)

Modalità d'esame

La valutazione dei risultati di apprendimento si basa sullo sviluppo di un progetto di gruppo, che si traduce nella produzione di adeguati artefatti, siano essi sotto forma di documentazione o software. L'esame finale si compone di due fasi: Una presentazione del progetto (su appuntamento), e Una prova orale che potrà coprire l'intero contenuto del corso (date fisse). La discussione del progetto con il docente del Modulo 3 deve avvenire prima dell'esame orale. La valutazione finale dipende dal livello e dall'ampiezza del progetto, dalla qualità della documentazione prodotta e degli artefatti software, nonché dal grado di conoscenza degli argomenti del corso dimostrato nella prova orale. La sede dell'esame è disponibile sul sito almaesami. Studenti/sse con DSA o disabilità temporanee o permanenti: si raccomanda di contattare per tempo l’ufficio di Ateneo responsabile (https://site.unibo.it/studenti-con-disabilita-e-dsa/it): sarà sua cura proporre agli/lle studenti/esse interessati/e eventuali adattamenti, i quali dovranno comunque essere sottoposti, con un anticipo di 15 giorni, all’approvazione del/della docente, che ne valuterà l'opportunità anche in relazione agli obiettivi formativi dell'insegnamento.

Testi di riferimento

Le slide e il materiale didattico (obbligatorio e facoltativo) saranno forniti durante il corso e saranno resi disponibili sul sito web del corso su Insegnamenti online.

Codice insegnamento 91257

Expert Systems 2° anno · 2° semestre · 6 CFU · INF/01 · 0 file
Final Examination 2° anno · 6 CFU · 0 file

La prova finale consiste nella presentazione di una tesi redatta in lingua inglese e corredata di un sommario in lingua inglese. Lo studente discuterà il lavoro svolto di fronte alla Commissione di Laurea Magistrale.

Scheda dell'insegnamento

Obiettivi formativi

La prova finale consiste nella presentazione di una tesi redatta in lingua inglese e corredata di un sommario in lingua inglese. Lo studente discuterà il lavoro svolto di fronte alla Commissione di Laurea Magistrale.

Codice insegnamento 86301

Final Examination If you select this activity, it means that you intend to write a thesis for which your continuous presence (in Unibo premises or at external companies/institutions) is NOT requested. 2° anno · Annuale · 24 CFU · 0 file

After completion of the dissertation students should be able to: - show evidence of a critical and holistic knowledge and have a deeper understanding of a specific topic concerning their chosen subject area; - understand…

Scheda dell'insegnamento

Obiettivi formativi

After completion of the dissertation students should be able to: - show evidence of a critical and holistic knowledge and have a deeper understanding of a specific topic concerning their chosen subject area; - understand the relationships between the theoretical concepts taught in class and their application, justifying the selective and critical use of material, data and interdisciplinary approaches adopted; - show evidence of ability to plan and manage a project within deadlines

Codice insegnamento 60750

INTRODUCTION TO QUANTUM COMPUTING 2° anno · 2° semestre · 6 CFU · INF/01 · 0 file

At the end of the course the student is acquainted with the basic mathematical notions underlying quantum computing seen as an alternative computing paradigm, and knows how to implement quantum algorithms as families…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course the student is acquainted with the basic mathematical notions underlying quantum computing seen as an alternative computing paradigm, and knows how to implement quantum algorithms as families of quantum circuits. Moreover, he has an understanding of more advanced topics like quantum cryptography, quantum error correction, and the development of graphical languages for quantum circuits.

Programma

First module:

  • overview on quantum computing
  • mathematical background: linear algebra and complex Hilbert spaces
  • qubits and their mathematical representation
  • a quantum computational model: quantum circuits
  • sample circuits (Deutsch, Bernstein-Vazirani)
    Second module:
  • quantum computational complexity
  • quantum algorithms (Simon, Grover, Shor)
  • quantum error correction
  • quantum protocols
  • overview on quantum programming and quantum graphical languages
  • quantum circuits optimization
  • post-quantum cryptography

Modalità d'esame

The exam consists in a seminar: during the course a list of in-depth study research papers will be made available, and each student will choose and present one of these papers. During the seminar there will be questions on the selected paper and on its relations with topics studied during the course. Upon agreement with professors, papers outside the selected list can be chosen, or the seminar may be replaced by project work.

Testi di riferimento

[1] P. Kaye, R. Laflamme, M. Mosca. An introduction to quantum computing. Oxford University Press, 2007. [2] M. Hirvensalo. Quantum computing. Springer, 2004.

Codice insegnamento B3567

ITALIANO DI BASE PER LE PROFESSIONI TECNOLOGICHE Solo per studenti stranieri privi di un'adeguata conoscenza della lingua italiana. 2° anno · 1° semestre · 3 CFU · 0 file

The course aims to provide students with some basic Italian language skills to help them enter the world of work. By the end of the course, students will be able to assess job opportunities in the technology sector,…

Scheda dell'insegnamento

Obiettivi formativi

The course aims to provide students with some basic Italian language skills to help them enter the world of work. By the end of the course, students will be able to assess job opportunities in the technology sector, draft a professional CV, and have the basic knowledge required to interact with human resources departments and technical staff within companies during the recruitment process.

Programma

The course covers the key linguistic and communicative aspects required to use Italian in professional contexts, with a particular focus on technology-related professions.
The course will cover the vocabulary used in the world of work and in technology-related professions, as well as useful expressions for describing one’s educational background, interests and professional skills.
Part of the course will be devoted to searching for job opportunities and understanding simple job advertisements, with a particular focus on requirements, skills, duties and working conditions.
Students will learn how to present their professional profile, describe their technical and soft skills, and draft a CV in Italian.
The course will also cover the main forms of professional written communication, through reading and writing simple application emails addressed to companies.
Finally, the course will include activities focused on the recruitment process, with exercises and mock job interviews with human resources staff and technical personnel from the company. Students will learn how to present their profile, answer simple questions about their career path and skills, and ask for clarification.

Modalità d'esame

La verifica finale consisterà nella realizzazione di un compito autentico articolato in più fasi: analisi di un'offerta di lavoro, presentazione del proprio profilo professionale, elaborazione di un curriculum vitae e partecipazione a una breve simulazione di colloquio.
La valutazione terrà conto della comprensione dei contenuti, dell'adeguatezza linguistica e comunicativa, della capacità di utilizzare il lessico professionale e dell'efficacia nella gestione delle situazioni comunicative proposte, in relazione al livello linguistico A1/A2.

Testi di riferimento

Pepe, D., Garelli, G. (2015), Al lavoro! Corso di italiano per stranieri in contesto lavorativo, Loescher Editore, livello A1-A2.
Pelizza, G., Mezzadri, M. (2015), Un vero affare! Corso di italiano per gli affari. Livello A2-B2, Torino, Loescher/Bonacci.

Codice insegnamento B8710

Internet of Things 2° anno · 2° semestre · 6 CFU · INF/01 · 0 file

At the end of the course, the student understands the architectures and methodologies at the basis of the Internet of Things (IoT) following a data centric approach. The student has a deep understanding of network…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student understands the architectures and methodologies at the basis of the Internet of Things (IoT) following a data centric approach. The student has a deep understanding of network protocols, integration of mobile and pervasive end-devices, middleware platforms for M2M-based IoT systems, edge/distributed/gateway computing principles, new services, service platforms and innovative application scenarios.

Programma

The course introduces the enabling technologies, programming languages, communication protocols, software architectures, and applications related to the emerging paradigm of the Internet of Things (IoT). In particular, the components of a typical IoT system are presented following a data-oriented approach, from data generation and processing on embedded systems and microcontrollers, through wireless transmission over WSAN/WLAN/WPAN networks, to data acquisition and storage on remote platforms, and finally to knowledge extraction using Artificial Intelligence (AI) techniques and their integration into edge computing environments through Edge AI and TinyML paradigms.
The course covers the following topics.
Introduction to IoT Systems
Definitions, application domains, and enabling technologies
IoT Components: Communication and Networking
Sensors and actuators; fundamentals of electronic circuit design (overview); sensing strategies and data acquisition. Wireless communication technologies and encoding techniques for IoT. Machine-to-Machine (M2M) communication: enabling wireless technologies for WPAN (e.g., Bluetooth Low Energy, IEEE 802.15.4, Z-Wave), WLAN, and LPWAN (e.g., LoRa, LoRaWAN). Network architectures and routing protocols (6LoWPAN, RPL).
IoT Components: Embedded Systems
Embedded systems: introduction and architectural patterns. Bare-metal and framework-based approaches (e.g., Arduino). Real-Time Operating Systems (RTOS), including FreeRTOS and ESP-IDF. Micro-interpreter-based approaches (e.g., MicroPython, WebAssembly). Interfacing microcontrollers with sensors and actuators through serial communication protocols.
IoT Components: Data Acquisition
Data acquisition protocols: CoAP, MQTT, and HTTP. Web of Things (WoT) and interoperability. IoT Components: Data Management and Analytics
Sensor data storage and processing.
Time series and time-series databases (InfluxDB). Time-series visualization using Grafana. Time-series forecasting using statistical methods. Time-series forecasting using AI and Machine Learning techniques. Edge AI and TinyML.
IoT Components: Edge/Cloud Architectures
Cloud, fog, and edge computing architectures for data storage and processing. IoT platforms, including AWS IoT, ThingSpeak, and related cloud services.

Modalità d'esame

The course includes an optional seminar and a mandatory project. The seminar takes place during the last week of the course and consists of a 20-30 minute presentation in which the student presents a research topic related to the course program, based on a scientific article or an existing tool. The seminar topic can be chosen from a list provided by the instructors or proposed by the student. The seminar is graded on a four-level scale (Fail, Pass, Good, Excellent).
The project involves developing an IoT system that implements the entire pipeline presented in the lectures (data acquisition from sensors, embedded system based on a microcontroller, data acquisition on an edge node using HTTP/CoAP/MQTT protocols, data storage with time-series databases, dashboards, data analysis/forecasting of time-series using AI/ML and statistical learning approaches). As with the seminar topic, the project outline can be proposed by the students and approved by the instructor, or directly proposed by the instructor. The project is graded out of 30.
The final grade is calculated considering the project grade and the seminar evaluation, based on the following conditions:
If the seminar is not taken, the maximum final grade attainable is 23. If the seminar is taken with a Pass evaluation, the maximum final grade attainable is 25. If the seminar is taken with a Good evaluation, the maximum final grade attainable is 28. If the seminar is taken with an Excellent evaluation, the maximum final grade attainable is 30 with honors.

Testi di riferimento

Instructor’s slides, links to book chapters, scientific articles, and online resources are provided on the course website.
Recommended textbook: Riccardo Melen, Vittorio Trecordi, IoT Networking, Pearson, ISBN 8891931934, ISBN13 978-8891931931, 336 pages (cover price 34 EUR).
Additional textbooks may be recommended during the course depending on the topics covered.

Codice insegnamento 81683

Internship Abroad for Preparation of the Final Examination If you select this activity, you intend to enter a competition for international mobility (e.g. Thesis Abroad, Erasmus+, etc.) or to start an internship by applying on SOL – Internship (to know mo 2° anno · 1° semestre · 18 CFU · 0 file

The student - is able to identify high-quality, coherent career opportunities - is able to use advanced tools and innovative techniques in professional settings, and to transfer knowledge and competences to novel work…

Scheda dell'insegnamento

Scheda dell'a.a. 2025/2026: quella dell'anno in corso non è ancora pubblicata.

Obiettivi formativi

The student - is able to identify high-quality, coherent career opportunities - is able to use advanced tools and innovative techniques in professional settings, and to transfer knowledge and competences to novel work environments, evaluating the results achieved during the preparation of the final exam.

Programma

Students can carry out their internship outside of Italy following one of the possibilities listed below: by participating in an international mobility programme, such as: Erasmus+ Mobility for Traineeship, grants for preparing the dissertation abroad; see also Internships abroad with international mobility programmes; by contacting a company/institution located abroad, and following the passages explained here. This internship allows the student to gain the first 12 credits associated with the final dissertation. To this end, (at least) 300 hours of activities (max. 360 hours) have to be conducted by the student in the company. Such activities have to be consistent with the project shared with the teacher who will play the role of thesis supervisor and the tutor within the company. Once agreed the topic of the final dissertation with the thesis supervisor and the external tutor, the student has to ask to add this type of internship to their career. Requests can be sent to the Internship office anytime, despite the 2 periods scheduled to change study plans; a specific form is needed (see https://corsi.unibo.it/2cycle/StatisticalSciences/internships). Once this request has been accepted, the student's study plan will be modified as follows: - the Master Thesis will be removed; - the following activities will be inserted: 84551 Internship abroad for Preparation of the Final Examination (12 cfu); Final Examination. Once the internship activities have been completed, the student must continue with the project agreed with the thesis supervisor in order to obtain the credits associated with the activity Final Examination. For more information see https://corsi.unibo.it/2cycle/StatisticalSciences/internships

Codice insegnamento 84551

Internship for Preparation for the Final Examination If you select this activity, you intend to start an internship by applying on SOL – Internship (to know more go on your degree course’s website > homepage > studying>internship for the preparation of th 2° anno · 1° semestre · 18 CFU · 0 file
Knowledge Engineering 2° anno · 2° semestre · 6 CFU · INF/01 · 0 file

At the end of the course, the student knows some (semi-)automated methods for joint interpretation of data and content as sources of knowledge. The student masters the basics of knowledge extraction, engineering, and…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student knows some (semi-)automated methods for joint interpretation of data and content as sources of knowledge. The student masters the basics of knowledge extraction, engineering, and linking, making data suitable to machine querying and automated reasoning, typically on decentralized platforms such as the Web.

Programma

Knowledge graphs and ontologies
Semantic Web standards: OWL, RDF, SPARQL
Ontology Design methodologies and ontology design patterns
Reasoning methods, neuro-symbolic reasoning
Large Language Models and Knowledge Engineering: applications and research challenges
Knowledge extraction use cases: text and music

Modalità d'esame

Group project: selected from a list proposed by the teachers (with individual assessment)
Project: The students will apply the semantic modeling methodologies acquired and experimented during the course, for the creation of a knowledge graph starting from existing resources (database, text, etc.), reusing / extending other ontologies and where necessary applying knowledge extraction tools, entity linking, ontology alignment, etc.
Teachers will assign a project to each group and will provide the specification for its realisation. Before the assignment each group will have the possibility to express two preferences on a list of available projects. Priority will be given to students' preference if possible, it cannot be guaranteed though that they will be addressed (in case of conflicts).

Testi di riferimento

Notes and slides provided by the teacher.
Hitzler, P., Gangemi, A., & Janowicz, K. (2016). Ontology Engineering with Ontology Design Patterns. Amsterdam: IOS Press.
P.A. Bonatti, S. Decker, A. Polleres, V. Presutti, Knowledge graphs: new directions for knowledge representation on the Semantic Web (dagstuhl seminar 18371). Dagstuhl Rep. 8(9), 29–111 (2019)
Aidan Hogan et. al. Knowledge graphs. ACM Computing Surveys, Vol. 54, No. 4, Article 71
Semantic Web (W3C Recommendations):
OWL 2: https://www.w3.org/TR/2012/REC-owl2-rdf-based-semantics-20121211/
RDF: https://www.w3.org/TR/2014/REC-rdf11-mt-20140225/
SPARQL: https://www.w3.org/TR/2013/REC-sparql11-query-20130321

Codice insegnamento 91265

Laboratory of Business Plan 2° anno · 1° semestre · 3 CFU · 0 file

At the end of the course, the student is able to account for and compare different theories that describe the starting up and organization of innovative ventures and understands the information and the analyses needed to…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student is able to account for and compare different theories that describe the starting up and organization of innovative ventures and understands the information and the analyses needed to perform a feasibility analysis and write a draft business plan for an innovative venture. The student is able to collect and analyze relevant information for that purpose, and to communicate a feasibility analysis/business plan orally and in writing.

Programma

The course operates as a practical laboratory, taking students step-by-step from idea generation to startup launch.
Introduction & The Entrepreneurial Opportunity: Understanding what a company and a startup are, the importance of the entrepreneurial team, and how to identify an idea.
The Deep-tech Startup Journey: Exploring the differences between deep-tech and regular-tech startups, the innovation ecosystem, key roles in a startup, and cap table composition.
Value Proposition & Market Analysis: Customer segments, Value Proposition Design, finding the problem-solution fit, and market sizing (TAM, SAM, SOM).
Business Model & Validation Strategy: The Business Model Canvas, validation approaches, and the Lean Startup methodology.
Financials & Fundraising: Developing a financial and economic plan, understanding funding sources, and exploring fundraising strategies.
From Business Model to Business Plan: Operationalizing assumptions, defining corporate strategy, and understanding the structure of a complete Business Plan.
Pitching Strategy: Learning how to successfully present a project, culminating in the "Final pitches" module.

Testi di riferimento

The following textbooks are strongly recommended for a clear comprehension of the topics presented during the course:
Preparing Effective Business Plans: An entrepreneurial approach. Bruce Barringer, 2014, Pearson New International Edition, 1st Edition, ISBN-13: 978-1-292-03991-6
Osterwalder, A., & Pigneur, Y. (2010). Business Model Generation: A Handbook for Visionaries, Game Changers, and Challengers. John Wiley & Sons, ISBN-13 ‏ : ‎ 978-8126533671
Alongside this textbooks, a series of slides, case studies, problems and exercises will also be presented throughout the course.

Codice insegnamento 91252

Machine Learning for Computer Vision 2° anno · 1° semestre · 6 CFU · ING-INF/05 · 0 file

At the end of the course, the student masters the most popular modern machine-learning approaches to computer-vision tasks, with particular reference to specialized deep-learning architectures. The student has both a…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student masters the most popular modern machine-learning approaches to computer-vision tasks, with particular reference to specialized deep-learning architectures. The student has both a theoretical understanding and the necessary practical skills required to develop state-of-the-art image and video analysis systems for real-world applications.

Programma

The course is held in the first semester, from September to December.
Topics:
Advanced CNNs: : ResNeXt and grouped convolutions, MobileNets, EfficientNet and RegNet. Attention and vision Transformers. Image classification architectures based on Transformers. Object detection. Introduction to ensemble learning via boosting. The Viola-Jones detector and its applications. Specialized neural network architectures for object detection. Two-stages, one-stage, and anchor-free detectors. Feature Pyramid Networks. Imbalanced learning and the focal loss. DEtection TRansformer (DETR) and the Hungarian loss. Hands-on session on object detection. Semantic/instance/panoptic segmentation. Ensemble learning via bagging and random forests. The algorithm behind the Kinect body part segmentation. Transposed and dilated convolutions. Fully Convolutional Networks, U-net, DeepLab. Instance segmentation and Mask R-CNN. Panoptic segmentation, MaskFormer. Metric learning. Deep metric learning and its applications to face recognition/identification and beyond. Contrastive and triplet loss, ArcFace, NT-Xent loss, CLIP. Hands-on session on metric learning. Image generation with GANs and diffusion models: metrics for generative tasks. Generative Adversarial Networks and Denoising Diffusion Probabilistic Models. Stable diffusion and text-guided image generation. Hands-on session on textual inversion.
Prerequisites:
Traditional Computer vision and image processing: image formation, image digitization, camera modelling and calibration, basic image manipulation and processing, local image features. PyTorch: a good intro is available at https://pytorch.org/tutorials/beginner/basics/intro.html Machine learning: supervised versus unsupervised learning, classification versus regression, underfitting and overfitting, regularization; data split in training, validation and test sets; hyper-parameters and cross-validation. Data-driven CV: layers in convolutional neural networks (convolutional layer, pooling, batch norm, fully connected layer, ReLU), basic CNN architectures (VGG, Inception, ResNet).
If you attended Computer Vision and Image Processing (either thought by Prof. Lisanti and me or by Prof. Di Stefano), you already fulfill these prerequisites. If you didn't, you can find on Virtuale slides and lab sessions.

Modalità d'esame

The assessment methods comprise of a theoretical part and a practical part.
The theoretical part is an oral exam. Students will present a recent scientific paper related to the course topics, previously agreed with the instructor. Then, students will answer questions on the paper and on the theory discussed in the course.
The practical part is an assignment on topics covered in the hands-on sessions and the theoretical lessons. The assignment must be submitted before sitting for the theoretical part.
The assignment is worth 10 points, the oral exam 22.
The oral exam aims to assess the student’s knowledge of the course content and their ability to understand and present in a limited amount of time a scientific paper related to the course's content.
Grade scale of oral exam:
Basic knowledge of the topics covered in the exam; some errors in the understanding of the presented paper or superficial understanding of it; generally correct language → 12–13 Solid knowledge of the topics covered in the exam; correct understanding of the presented paper; correct language use → 14-17 Thorough knowledge of the topics covered in the exam and ability to reason critically on them; very good understanding of the presented paper; mastery of subject-specific terminology → 18-20 Excellent knowledge of the topics covered in the exam and ability to reason critically about them; complete understanding of the paper and of the most relevant referenced works; full command of subject-specific terminology → 21-22
Grade scale for the assignment:
Basic implementation of the task; code is functional but contains errors, lacks structure, or is difficult to follow; minimal experimentation and little to no discussion of results; metrics may be reported but not properly interpreted; limited or unclear exposition → 6 Correct implementation of the task; results are reproducible; code is organized and mostly readable; metrics are computed and reasonably interpreted; some empirical analysis or comparison of alternatives is present; exposition is clear, though not always thorough → 7–8 Well-structured and readable code; clear and reproducible workflow; solid experimentation with ablation studies or meaningful comparisons; good understanding of metrics; explanations show thoughtful reflection and interpretation of results → 9 Excellent and well-structured submission; clear motivation behind design choices; critical and well-documented experimental procedure, including insightful ablations or comparisons; results are convincingly interpreted and contextualized; all material (code, text, plots) is cohesive and professionally presented → 10
AI policy for the assignment: limited and non-substantial use of AI is allowed as a support tool (e.g, code debug, code documentation). Substantial use of AI to complete parts of the project is not permitted (e.g., generate the code for the full assignment or a large part of it). Use of AI tools must be explicitly disclosed by the students. Students are ultimately responsible for the delivered notebook. If a significant discrepancy between the disclosed AI used and the submitted assignment is perceived while grading it, a supplementary oral exam will be performed when sitting for the theoretical part.

Testi di riferimento

The main reference material will be the slides and notes provided on Virtuale by the instructor. A set of pointers to scientific papers and technical reports for each topic will also be provided during lectures.
Several freely-available on-line resources can be useful to complement the material provided by the instructor on Virtuale.
https://udlbook.github.io/udlbook/ Simon J.D. Prince, "Understanding Deep Learning", MIT Press, 2023. http://d2l.ai/ - Aston Zhang and Zachary C. Lipton and Mu Li and Alexander J. Smola "Dive into Deep Learning", 2020 http://www.deeplearningbook.org/ - Ian Goodfellow and Yoshua Bengio and Aaron Courville, "Deep Learning", 2016. https://github.com/fastai/fastbook - Jeremy Howard and Sylvain Gugger, "Deep Learning for Coders with fastai and PyTorch", 2020 https://pytorch.org/assets/deep-learning/Deep-Learning-with-PyTorch.pdf - Eli Stevens, Luca Antiga, and Thomas Viehmann, "Deep learning with PyTorch", July 2020.

Codice insegnamento 91266

Multi-Agent Systems 2° anno · 2° semestre · 6 CFU · ING-INF/05 · 0 file

At the end of the course, the student understands the conceptual and technical foundation of multi-agent systems, and is able to model complex computational and socio-technical systems in terms of agent-oriented…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student understands the conceptual and technical foundation of multi-agent systems, and is able to model complex computational and socio-technical systems in terms of agent-oriented abstractions; build complex computational and socio-technical systems using agent-oriented technologies and methodologies; design and engineer intelligent systems as multi-agent systems, by integrating techniques and methods from artificial intelligence in an effective and methodologically-sound way.

Programma

  • General Issues of Multi-Agent Systems Drivers for Intelligent Systems • Agents for Complex Distributed Systems • On Autonomy. Concepts & Definitions • Artefacts for Agents. Function and Use in MAS • Automated Reasoning • Reasoning Agents • Coordination of Multi-Agent Systems • Self-Organising Systems • Nature-Inspired Coordination & Self-Organisation • Simulation & Multi-Agent Systems: An Introduction
  • Technologies for Multi-Agent Systems Agents in JADE • Programming Intentional Agents: Exercises in Jason
  • Scientific Competences Sources of Scientific Literature for Intelligent & Autonomous Systems • Systematic Literature Review. A Methodology for Scientific Surveys

Modalità d'esame

The assessment of the learning achievements is based on the development of an individual/group project, which results in the production of suitable artefacts, either documental or software.
The final test consists in the oral discussion of the project.
Final evaluation depends on the level and extent of the project, the quality of the document and software artefacts produced, and the degree of knowledge on the course's subjects demonstrated in the final discussion.

Testi di riferimento

The bibliography is made available through the course web site.

Codice insegnamento 91267

Multimedia Data Management M 2° anno · 2° semestre · 6 CFU · ING-INF/05 · 0 file

At the end of the course, the student has the knowledge and skills required for an effective and efficient management of multimedia (MM) data, with particular attention to the problems of MM data representation, MM…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student has the knowledge and skills required for an effective and efficient management of multimedia (MM) data, with particular attention to the problems of MM data representation, MM data retrieval models, and interaction paradigms between the user and the MM system both for purposes of data presentation and exploration. The student understands the architecture of traditional and advanced MM systems and services, search engines, social networks and recommendation systems.

Programma

The course intends to provide students with methodology, modeling, design, and implementation skills/expertise related to the development of smart "MM data-intensive" applications and services like the the ones included in commercial solutions like Google search engine, YouTube, Facebook, Instagram, Flickr, and Twitter, just to named a few, but especially possible smarter extensions.
Constraints on previous knowledge: nothing. The course has no specific prerequisites in terms of master's degree skills; it only requires a bachelor's degree in "computer science" area (i.e., computer engineering, computer science, etc.).
COURSE CONTENTS:
Basics on Multimedia Data Management
Multimedia data and content representations
MM data and applications MM data coding MM data content representation
How to find MM data of interest
Description models for complex MM objects Similarity measures for MM data content MM Data Base Management Systems
Efficient algorithms for MM data retrieval
MM query formulation paradigms Sequential retrieval of MM data Index-based retrieval of MM data
Automatic techniques for MM data semantic annotations
Browsing MM data collections MM data presentation
User interfaces Visualization paradigms Dimensionality reduction techniques
Result accuracy, use cases and real applications
Quality of the results and relevance feedback techniques Use cases and demos of some applications
Multimedia Data on the Web
Web search engines Graph-based data: semantic Web and social networks Web recommender systems
N.B. For students of the second cycle degree programmes (LM) in Artificial intelligence and Computer Science, the "Efficient algorithms for MM data retrieval" part of the program (that counts the 2 extra CFU with respect to the 8 CFU of the master course in Computer Engineering) is not required for the final exam.
N.B. Students can decide to take the final exam in English or Italian.

Modalità d'esame

Achievements will be assessed by the means of a final exam. This is based on an analytical assessment of the "expected learning outcomes" described above. In order to properly assess such achievement the examination is composed of an oral exam.
The admission of the students to the final examination is constrained to the upload of the complete practical project into the dedicated OneDrive folder "MDM", following the instructions provided by the teacher (see the slides of the course presentation for more details).
To participate to the final exam, interested students have to register themselves by exploiting the usual UniBO Web application, called AlmaEsami.
Higher grades will be awarded to students who demonstrate an organic understanding of the subject, a high ability for critical application, and a clear and concise presentation of the contents. To obtain a passing grade, students are required to at least demonstrate a knowledge of the key concepts of the subject, some ability for critical application, and a comprehensible use of technical language. A failing grade will be awarded if the student shows knowledge gaps in key-concepts of the subject, inappropriate use of language, and/or logic failures in the analysis of the subject.

Testi di riferimento

Education material provided by the teachers (copies of the slides used in the classroom, scientific literature, bibliography, and useful links). For more details, refer to the dedicated Web site: http://www-db.disi.unibo.it/courses/MDM/.

Codice insegnamento 77933

Natural Language Processing 2° anno · 1° semestre · 6 CFU · ING-INF/05 · 0 file

At the end of the course, the student masters the basic algorithms, tools and systems for the management, processing and analysis of natural language. The student is able to design and develop simple systems oriented…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student masters the basic algorithms, tools and systems for the management, processing and analysis of natural language. The student is able to design and develop simple systems oriented to real-world natural language processing applications such as those requiring segmentation and classification of elements of text.

Programma

Topics
Introduction to NLP Elements of computational linguistics Basic text processing Language modeling with n-grams Text classification using linear models Vector semantics and embeddings Neural language modeling RNNs for sequence processing Contextual word embeddings, attention and transformers Large language models Basics of information retrieval Elements of speech processing NLP libraries and tools NLP applications
Prerequisites
The course is intended for 2nd-year students of the Masters' Degree in Artificial Intelligence, who have a solid background in foundational subjects and technological tools for tackling modern Natural Language Processing. There are no formal prerequisites in terms of exams taken, but students are expected to be familiar with machine learning and deep learning concepts and tools, and the Python programming language.

Modalità d'esame

The course will include graded assignments, to be solved individually or in groups of up to 3 students, and a closed-book written exam, to be sat individually after submitting the assignments.
The written exam is intended to assess the degree of understanding of the course topics. Assignments are intended to assess the student's ability to solve a small-scale NLP task. Access to the written exam is possible only after submitting the assignments by the relevant cut-off date. There will be three cut-off dates:
early January end of May end of August
The exact dates are published on the Virtuale platform. The last cut-off date is also the deadline for submitting assignments for this academic year. Once submitted, assignments are valid for the whole academic year and grant access to all subsequent written exam sessions until the end of the academic year.
Assignments are graded according to methodological soundness, quality and documentation of the submitted solution. Written exams are graded according to the correctness and comprehensiveness of the answers. Solutions to assignments or written exams that demonstrate an outstanding mastery of the course topics are awarded 0.5 extra points.
Assignments submitted by the first cut-off date (mid January) are awarded 0.5 bonus points.
The final grade is the sum of all the grades obtained with assignments and written exam. Half points are rounded up until 30. After 30 there is no rounding up. "30 cum laude" requires reaching 31 points.
Use of AI during the written exam
Regarding learning assessment, the use of AI is prohibited. Any use constitutes a violation of academic integrity.
It is permitted to use AI to some extent in the solution of the assignments, as detailed in the assignment section in Virtuale.

Testi di riferimento

Speech and Language Processing, by Dan Jurafsky and James H. Martin. 3rd Ed. draft Other resources and scientific articles that will be made available throughout the course.

Codice insegnamento 91258

Preparation for the Final Examination Abroad If you select this activity, you intend to enter a competition for international mobility (e.g. Thesis Abroad, Erasmus+, etc.). You will agree with your thesis supervisor the company/institution who will host y 2° anno · 1° semestre · 18 CFU · 0 file

Lo studente acquisisce un’esperienza in uno degli ambiti professionali di possibile futuro impiego attraverso un lavoro di ricerca all'estero finalizzato alla preparazione della prova finale.

Scheda dell'insegnamento

Scheda ripresa da un altro corso di laurea dello stesso ateneo.

Obiettivi formativi

Lo studente acquisisce un’esperienza in uno degli ambiti professionali di possibile futuro impiego attraverso un lavoro di ricerca all'estero finalizzato alla preparazione della prova finale.

Programma

For those students who will opt for the preparation of the final thesis abroad, the final exam will be divided into two parts: the final exam itself and the preparation of the final thesis abroad. Thus, the student's study plan will be modified as follows:

  • the Master Thesis will be removed; - the following activities will be inserted:
    84548 Preparation for the Final Examination Abroad (12 cfu); Final Examination.
    To go abroad and work on the final thesis, students are required to do research on a subject shared with the Unibo teacher who will play the role of thesis supervisor and an external researcher based abroad. Once the research activities abroad have been completed, the student must continue with the project agreed with the thesis supervisor in order to obtain the credits associated with the activity Final Examination.
    Study grants for dissertations abroad for Unibo students at the Department of Statistical Sciences are regularly provided. For more information on these grants see https://corsi.unibo.it/2cycle/StatisticalSciences/study-grant-for-dissertations-abroad

Codice insegnamento 84548

Project Management and Soft Skills M 2° anno · 1° semestre · 3 CFU · 0 file

At the end of the course, the student is able to acquire the necessary skills to be a successful engineer, with a particular focus on non-technical (also known as soft) skills such as…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student is able to acquire the necessary skills to be a successful engineer, with a particular focus on non-technical (also known as soft) skills such as inductive/deductive/analytical/design reasoning, communication skills and employability. The student is able to use the basic tools of project management, including Gantt and Pert diagrams, work package breakdown, project cost estimation, and relevant aspects.

Programma

The syllabus is reported below. The course requires attendance.
I.Introduction (approx 3 hours).
II. A Pragmatic Approach to Project Management (approx 9 hours).

  • Projects, Roles, WBS
  • Gantt and PERT Diagrams
  • Cost Assessment
  • Submitting a Project Proposal
    III. Soft Skills and Aptitudes (approx 9 hours).
  • Introduction to Cognitive Processes
  • Human Behaviour
  • Success and Talent
  • Aptitudes
  • Team Work
  • Leadership
    IV. Communication Skills (approx 9 hours).
  • Fundamentals of Human Communication
  • Persuasion
  • Inter-Personal Communication
  • Presentation Skills
    The course will possibly include one seminar offered by a professional.

Modalità d'esame

Prior to the date of the exam (one week earlier) the student will deliver to the instructor:
1) a research project proposal, including a WBS, Gantt and PERT diagrams;
2) his/Her CV with a cover letter, simulating the application for a job position as project manager;
3) a slideset for a five-minute pitch.
By the day before the exam date, the student will be informed whether they can be admitted to the exam.
On the day of the exam, the student will undergo a written questionnaire plus an oral exam. The written questionnaire will include close-answer questions on the theoretical aspects addressed by the course. During the oral exam, the student will present in five minutes the slideset prepared.
More precise criteria for assessment will be provided during the lectures.

Testi di riferimento

Slidesets. Several books will be suggested for additional reading during the classes. None of them is specifically useful to cover the contents of the course. The course requires attendance.

Codice insegnamento 81799

Project Work in Architectures and Platforms for Artificial Intelligence 2° anno · 1° semestre · 3 CFU · 0 file

At the end of the course, the student is able to apply the knowledge acquired in Architectures And Platforms For Artificial Intelligence in order to carry out autonomously a project focusing on a topic agreed upon with…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student is able to apply the knowledge acquired in Architectures And Platforms For Artificial Intelligence in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Programma

This course involves the design, development and analysis of a substantial software artifact for a parallel platform of choice (typically C/OpenMP or CUDA/C, although it will be possible to investigate other languages). The software can consist of either the parallelization of some existing program, or the development of a new program to solve some problem. In both cases the topic must be discussed and agreed upon with the instructor.
The technologies that will be used include:
Shared-Memory programming with C/OpenMP: basic costeructs, work-sharing costructs, scoping directives GPU programming with CUDA/C: CUDA architecture and memory hierarchy, CUDA/C programming costructs, threads and thread blocks, efficiency considerations Other technologies for parallel programming could also be considered

Modalità d'esame

The final exam consists of the development of a parallel program that must be correct and well documented, and must be accompanied by a written report. The final grade will depend on the quality of both the program and the written report.

Testi di riferimento

Peter Pacheco, Matthew Malensek, An Introduction to Parallel Programming , Morgan Kaufmann, 2020, ISBN 978-0128046050 CUDA C programming guide [http://docs.nvidia.com/cuda/cuda-c-programming-guide/]

Codice insegnamento 91279

Project Work in Artificial Intelligence and Robotics 2° anno · 1° semestre · 3 CFU · 0 file
Project Work in Artificial Intelligence in Industry 2° anno · 1° semestre · 3 CFU · 0 file

At the end of the course, the student is able to apply the knowledge acquired in Artificial Intelligence In Industry in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student is able to apply the knowledge acquired in Artificial Intelligence In Industry in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Programma

A mid-sized project on a topic related to the contents of the "AI in the industry" course. Typically, this will be an extension of the project work for the final exam of the course itself.
Students can choose whether to focus on a specific application, or on a methodological contribution that may impact several application domains.
In any case, the project topic must be approved by the teacher before actual work can commence. This is done to avoid too difficult topics as much as too easy ones.

Modalità d'esame

Presentation + discussion on the project topics. In case the project is an extension for the main exam work, a separate presentation and discussion will still be needed.
The project code must also be delivered.

Codice insegnamento 91283

Project Work in Big Data Analytics and Text Mining 2° anno · 1° semestre · 3 CFU · 0 file

At the end of the course, the student is able to apply the knowledge acquired in Data Mining, Text Mining And Big Data Analytics in order to carry out autonomously a project focusing on a topic agreed upon with the…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student is able to apply the knowledge acquired in Data Mining, Text Mining And Big Data Analytics in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Programma

The project work - which can be combined with the project exam of Big Data Analytics and Text Mining and/or master thesis and also with the compulsory NLP course - is agreed upon with one of the course instructors and can cover any topic in AI, including Data Mining, Text Mining and Natural Language Processing, Big Data Analytics etc.

Codice insegnamento B3157

Project Work in Combinatorial Optimization 2° anno · 1° semestre · 3 CFU · 0 file

At the end of the course, the student is able to apply the knowledge acquired in Combinatorial Optimization in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student is able to apply the knowledge acquired in Combinatorial Optimization in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Programma

This teaching activity is about developing a project in combinatorial optimization, following the course 91762 - Combinatorial Decision Making and Optimization (CDMO). Upon request, the teaching stuff can offer suggestions and help in defining the topic and objective of the project work. The student is, however, encouraged to take the initiative by reviewing the relevant literature and proposing a project work, for instance, about:
other CDMO approaches not covered in the course; hybridization of different CDMO approaches; hybridization with data-driven AI (ML/DL/Generative AI); challenging applications; literature survey on a research topic.
The proposal has to be approved by the teaching stuff before the student starts working on the project. Working as a group is a possibility depending on the project complexity.

Modalità d'esame

Project report and presentation.

Testi di riferimento

Scientific papers and pointers provided by the teaching staff, in addition to the readings and bibliography of the course 91762 - Combinatorial Decision Making and Optimization.

Codice insegnamento 91276

Project Work in Deep Learning 2° anno · 1° semestre · 3 CFU · 0 file

At the end of the course, the student is able to apply the knowledge acquired in Deep Learning in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student is able to apply the knowledge acquired in Deep Learning in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Programma

To be agreed upon with the teacher.

Codice insegnamento 91274

Project Work in Fundamentals of Artificial Intelligence and Knowledge Representation 2° anno · 1° semestre · 3 CFU · 0 file

At the end of the course, the student is able to apply the knowledge acquired in Fundamentals of Artificial Intelligence and Knowledge Representation in order to carry out autonomously a project focusing on a topic…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student is able to apply the knowledge acquired in Fundamentals of Artificial Intelligence and Knowledge Representation in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Codice insegnamento 91270

Project Work in Image Processing and Computer Vision 2° anno · 1° semestre · 3 CFU · 0 file

At the end of the course, the student is able to apply the knowledge acquired in Image Processing And Computer Vision in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student is able to apply the knowledge acquired in Image Processing And Computer Vision in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Programma

See "91254 - Image Processing and Computer Vision"

Modalità d'esame

The project work requires that:
The student should provide a list of articles, preferably with available source code. The choice should be based on articles published in the conferences or journals listed in the introductory lesson of the IPCV course. One article will be selected from the list proposed by the student. The student must study the chosen article and its source code to replicate at least one experiment mentioned in the article. The experiment conducted by the student must involve both the training and evaluation phases of the model and must be agreed upon with the Professor. Finally, the student will prepare a presentation that describes the technique proposed in the selected article and the experiment conducted.
During the presentation, questions will be asked regarding the student's work.

Testi di riferimento

See "91254 - Image Processing and Computer Vision"

Codice insegnamento 91277

Project Work in Internet of Things 2° anno · 1° semestre · 3 CFU · 0 file

At the end of the course, the student is able to apply the knowledge acquired in Internet Of Things in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student is able to apply the knowledge acquired in Internet Of Things in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Programma

The course is based on a set of project proposals focusing the Internet of things class topics, which can be selected by candidates (also proposed by candidates). The project proposal must be agreed with the teacher and formally assigned to each single candidate.
The project realization will lead to a platform, system or software, possibly mutually integrated, for the realization of IoT applications, research and development objectives.

Modalità d'esame

The project work can be selecetd by a set of proposals (or proposed by the candidates) and must be formally agreed and approved by the teacher.
After the project realization, the assessment method is based on the illustration of the project work by creating a final report and a demo/presentation of the project (based on slides). The presentation will be based on a oral session focusing the objectives, state of the art, solutions and methodologies, design, realization, tests and validation.
The evaluation will be based 70% on the methodological approach, design, realization and tests, and for the remaining 30% based on quality of the presentation, reports and documents realized.

Testi di riferimento

Material, scientific papers, web documents will be supplied during the Internet of Things class.

Codice insegnamento 91286

Project Work in Knowledge Engineering 2° anno · 1° semestre · 3 CFU · 0 file

At the end of the course, the student is able to apply the knowledge acquired in Knowledge Engineering in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student is able to apply the knowledge acquired in Knowledge Engineering in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Programma

Students will develop a project, under the supervision of the teacher. The project can be both individual or developed in group (of max three students). The topic and the goals of the project will be identified and agreed case by case but they will be relevant for the knowledge engineering area. A non-complete list of application areas is the following:
knowledge engineering automation knowledge graph creation from text ontology engineering question answering based on knowledge graphs knowledge graph visualisation knowledge graph embeddings ontology / knowledge graph matching development of Protégé plugins for ontology design development of ontology and knowledge graph visualisation tools LLMs and knowledge graphs
A non-exhaustive list of available projects is the following:
Learning from and integrating common sense resources to enable common sense reasoning Implementation of a method for question answering over knowledge graphs Developing a tool for supporting semi-automatic ontology testing Developing a framework for automatic ontology evaluation Implementation of a visualisation tool for ontology and knowledge graph summarisation Knowledge extraction from text for populating knowledge graphs Knowledge extraction from audio and/or music notations for populating knowledge graphs Music recommendation based on knowledge graphs Populating and refining knowledge graphs with games Evaluating LLMs in supporting knowledge engineering tasks Evaluating LLMs performance when combined with knowledge graphs and ontologies

Modalità d'esame

Delivery, presentation and discussion of the project.

Testi di riferimento

References will be provided by the teacher according to the specific project.

Codice insegnamento 91287

Project Work in Languages and Algorithms for Artificial Intelligence 2° anno · 1° semestre · 3 CFU · 0 file

At the end of the course, the student is able to apply the knowledge acquired in Languages and algorithms for Artificial Intelligence in order to carry out autonomously a project focusing on a topic agreed upon with…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student is able to apply the knowledge acquired in Languages and algorithms for Artificial Intelligence in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Programma

The contents of the project will be agreed with the teachers in charge of the course.

Modalità d'esame

The project work consists of the study and analysis of one or more research papers related to one of the topics covered in the two integrated courses, the preparation of a short report, and the presentation of the obtained results to the teachers.

Testi di riferimento

Dirk van Dalen. Logic and structure. 4th edition, Springer.
K. Doets. From Logic to Logic Programming. The Mit Press.
Russell, Norvig. Artificial Intelligence: A Modern Approach (any edition). Pearson.
Sanjeev Arora and Boaz Barak, Computational Complexity: Modern Approach. Cambridge University Press, 2009.
Michael Kearns, Umesh. Vazirani. An Introduction to Computational Learning Theory. MIT Press, 1994.
Shai Shalev-Shwartz and Shai Ben-David. Understanding Machine Learning: From Theory to Algorithms. Cambridge University Press, 2014.

Codice insegnamento 91275

Project Work in Machine Learning and Data Mining 2° anno · 1° semestre · 3 CFU · 0 file

At the end of the course, the student is able to apply the knowledge acquired in Machine Learning in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student is able to apply the knowledge acquired in Machine Learning in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Programma

The professor assigns a dataset and a mining task to be developed on it among three proposals made by the student. For asking the assignment of the dataset do the following:
visit the Kaggle [https://www.kaggle.com/] website; choose three competitions of your interest, either active or closed; the dataset should be fairly complex, in other words, avoid very small datasets with a few hundred elements and a handful of columns; (the competitions are considered only as the source of the problem and the data, it is not required to participate to the competition, all the competitions can be considered, both the open and the closed ones); send and email to the teacher with the subject "[Project work] Kaggle competitions choice" and containing the link to the three competition of your interest wait for the answer and, when the competition is assigned, do as specified on the "Assessment methods section below"
As an alternative, if you are interested to a specific project related to machine learning, prepare a short description of your idea and ask for an appointment.

Modalità d'esame

This activity is mainly oriented to develop abilities based on the knowledge acquired in the related course.
After the assignment of the task by the teacher:
create a github project named “surname-projecttitle” and share it with the teacher; create a readme.md describing the project, with objectives, results, pertinent references, and anything else that may be useful for understanding create a sub-folder where software and data will be delivered, or including permanent links to the data if the data is too large Structure: the folder must contain a readme.md with the project description, the reference to the Kaggle challenge, the installation and startup notes, and the prerequisites for operation Solution: the solution must be produced as one or more python notebooks; each notebook must have a clear workflow description at the top, with numbered steps, and comments along the notebook, with the major points numbered consistently with the workflow at the beginning; before uploading the notebook it is preferable do a reset and a clean run, in order to have the cells numbered consistently from 1; clean errors and warnings, avoid long and scarcely informative outputs (export the notebook also as a pdf in landscape format); Software quality: the software must be commented in English, the names of the variables must be meaningful and inspired by English Complexity of the project: it must be proportional to 75 hours of full-time work of a good machine learning and Python expert. Caveat: most of the Kaggle competition have several data files, and among them "train.csv" and "test.csv". The train file is "supervised", while the test file does not have the target, therefore it is used only for participating to the Kaggle competition, or for other unsupervised activities, not for your project. For your project use only the train file, splitting it as required for doing training, validation and testing. prepare a latex beamer presentation of 15-20 slides, deliver it on a doc subfolder on GitHub containing the .tex with any complementary files and the pdf agree with the teacher a date for the presentation and possible demonstration of the software Unless otherwise indicated at the time of assignment, the indicative delivery date should be within three months after assignment at any time it is possible to consult the teacher by e-mail or by requesting an appointment delays are not a problem, please, at the expiry of the three months, notify via e-mail the need to continue

Testi di riferimento

Documentation provided by the teacher or publicly available.

Codice insegnamento B3155

Project Work in Machine Learning for Computer Vision 2° anno · 1° semestre · 3 CFU · 0 file

At the end of the course, the student is able to apply the knowledge acquired in Machine Learning For Computer Vision in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student is able to apply the knowledge acquired in Machine Learning For Computer Vision in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Programma

See "91266 - Machine Learning for Computer Vision" contents.

Modalità d'esame

Students are required to carry out and present a software project that solves a computer vision problem by means of machine learning or deep learning algorithms. The project can be proposed either by the instructor or by a (group of) student(s), up to three.
The assessment consists in a written report and an oral discussion about the project.
The grade is pass/fail.

Testi di riferimento

See "91266 - Machine Learning for Computer Vision" bibliography.

Codice insegnamento 91288

Project Work in Multi-Agent Systems 2° anno · 1° semestre · 3 CFU · 0 file

At the end of the course, the student is able to apply the knowledge acquired in Multi-Agent Systems in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student is able to apply the knowledge acquired in Multi-Agent Systems in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Programma

To be agreed upon with the teacher.
See the project page of the course.

Modalità d'esame

Individual / group project discussion.

Codice insegnamento 91289

Project Work in Multimedia Data Management M 2° anno · 1° semestre · 3 CFU · 0 file

At the end of the course, the student is able to apply the knowledge acquired in Multimedia data management M in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student is able to apply the knowledge acquired in Multimedia data management M in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Programma

A scientific paper is usually considered as the base for the development of a multimedia data management algorithm and/or infrastructure and/or application/service and/or interface. However, everything that “looks interesting” can be a good project topic candidate! :)

Modalità d'esame

Power point presentation and project demo.

Testi di riferimento

Scientific papers provided by the teacher. For more details, refer to the dedicated Web site: http://www-db.disi.unibo.it/courses/MDM/.

Codice insegnamento 93103

Project Work in Natural Language Processing 2° anno · 1° semestre · 3 CFU · 0 file

At the end of the course, the student is able to apply the knowledge acquired in Natural Language Processing in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student is able to apply the knowledge acquired in Natural Language Processing in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Programma

This teaching activity is about developing a project in natural language processing or natural language understanding, following the course 91258 - Natural Language Processing. Upon request, the teaching staff can offer suggestions and help in defining the topic and objective of the project work. The student is, however, encouraged to take the initiative by reviewing the relevant literature and proposing a project work, for instance, about:
exploring a foundational aspect; exploring NLP methods for low-resource languages or languages other than English; working on a challenging application; working on a research topic; preparing a literature survey on a research topic; significantly expanding a project developed within the NLP course.
The proposal has to be approved by the teaching staff before the student starts working on the project. Working as a group is encouraged.
Particularly innovative projects may receive extra support aimed to a possible submission of the work to a relevant scientific event.

Modalità d'esame

Project report and presentation, in presence. Exception apply (see below). The project report must be uploaded on the virtuale platform at least 1 week before the presentation date. Dates for project work presentation will be published periodically on AlmaEsami. In case of particular needs to obtain credits by a deadline, if no dates are published in the following months, you should contact the teacher by email to ask a date. Please specify "NLP Project Work presentation" in the subject.
Use of AI
The work materials produced and submitted will be validated through the oral interview for compliance with the policy on the use of AI (see "teaching tools").
Possibility of remote presentation
All project presentations must be done in presence. Exceptions are granted only in cases of continued impossibility of traveling from abroad due to force majeure (conflicts, epidemics) or if the student is abroad for the preparation of the final exam. Sitting an exam at the University of Bologna, even remotely, during the Erasmus+ period is not allowed.

Testi di riferimento

Scientific papers and pointers provided by the teaching staff, in addition to the readings and bibliography of the course 91258 - Natural Language Processing.

Codice insegnamento 91278

Project Work in User Experience Design 2° anno · 2° semestre · 3 CFU · 0 file

At the end of the course, the student is able to apply the knowledge acquired in User Experience Design in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student is able to apply the knowledge acquired in User Experience Design in order to carry out autonomously a project focusing on a topic agreed upon with the teacher.

Programma

The module is a follow-up of the main course in Usability and User Experience Design specifically meant for students in Artificial Intelligence and discusses the following topics:
Understand that (artificial) intelligence is not just about learning and reasoning, but also about communicating (e.g. explaining to humans). Understand what is the state-of-the-art of eXplainable AI (XAI) and how to design user-centred explanatorY AI (YAI).

Modalità d'esame

The same as the main course in Usability and User Experience Design

Testi di riferimento

The same as the main course in Usability and User Experience Design

Codice insegnamento 91285

Scalable and Reliable Services M 2° anno · 2° semestre · 8 CFU · ING-INF/05 · 0 file

Digital services have to meet various requirements in terms of performance, scalability and reliability. We analyze the whole lifecycle of high quality services, from design to deployment, testing and operation. In…

Scheda dell'insegnamento

Scheda dell'a.a. 2025/2026: quella dell'anno in corso non è ancora pubblicata.

Obiettivi formativi

Digital services have to meet various requirements in terms of performance, scalability and reliability. We analyze the whole lifecycle of high quality services, from design to deployment, testing and operation. In each phase, we aim to provide the students with the ability to gather and analyze data, to identify sources of outages and critical dependencies, and to avoid bottlenecks and single points of failure. Finally, we expect students to be prepared to evaluate and discuss alternatives and justify investment in support of business services.

Programma

Introduzione • Servizi cloud • Architetture di provider cloud • Servizi di alta qualità: prestazioni, scalabilità, affidabilità (e sicurezza) • Ciclo di vita di servizi di alta qualità Parte 1: Architetture per servizi scalabili e affidabili • Fonti di interruzioni e dipendenze critiche • Colli di bottiglia e single point of failure • Design: valutazione della maturità, principi architetturali per affidabilità e scalabilità, modello cubo in scala AKF • Migrazione al cloud • Gestione dei dati critici: Strategia, Governance, Management • Alternative di implementazione su piattaforme cloud e multi-cloud Parte 2: Distribuzione del servizio • Produzione di software sicura e robusta • DevOps sicuri e robusti • Laboratori su piattaforme cloud Parte 3: Test • Analisi comparativa • Test delle prestazioni • Stress testing Parte 4: Organizzazioni scalabili e affidabili • Ruoli e responsabilità • Leader e manager • Mettere tutto insieme • Capacity planning • Comprendere e gestire la complessità • Gestione dei cambiamenti Parte 5: Problemi, incidenti e crisi • Monitoraggio delle prestazioni • Segnali di malfunzionamenti operativi • Gestione degli incidenti • Gestione della crisi

Modalità d'esame

Vi sono due possibilità di esame. (1) Progetto software (max 3 studenti), presentazione dei risultati e spunto per la discussione dei temi del corso (2) Attività progettuale individuale durante l'esame, presentazione dei risultati e prova orale. Gli studenti interessati all'opzione (1) devono completare l'esame entro la fine di luglio 2024.

Testi di riferimento

Slide, dispense del docente, capitoli di libro, articoli scientifici e risorse online disponibili sul sito di Virtuale.

Codice insegnamento 97431

Social Network Analysis 2° anno · 1° semestre · 6 CFU · INF/01 · 0 file

At the end of the course, students gain knowledge on the Web as a socio-technical system involving specific processes, entities, and behaviours, using interdisciplinary methods that blend computer science, sociology,…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, students gain knowledge on the Web as a socio-technical system involving specific processes, entities, and behaviours, using interdisciplinary methods that blend computer science, sociology, ethnography, economics, linguistics, etc. The students are able to analyse the Web phenomena similarly to typical objects from natural sciences, distinguishing between data and applications, agents from computationally generated profiles, and addressing the characteristics of networks of entities emerging from the informationl, physical, social, and conceptual spaces constituting the Web.

Programma

The programme is the same for both attending and non-attending students:
Introduction to Network Analysis, gentle introduction to the field of network analysis and its usages in other fields of research (e.g., computer science, forensics, archeology, literature, history, science of religion, etc.). Research Design and How to Read a (Network Analysis) Research Paper: introduction to the scientific publication process, elements of research papers (on network analysis), research design, analysis of research papers. Mathematics of Networks: networks and their representation, types of networks, graph representations, paths and components, adjacency matrices and matrix representations, ways and modes, operations on Matrices. Data Collection and Data Management: network questions, data collection and reliability, data formats and transformation, algorithms and software for network analysis and visualisation. Measures and Metrics, Nodes: kinds of measures, multi-category nominal scales, ordinal and scalar measures, centrality, degree and other kinds of centrality (e.g. Google's PageRank), hubs and authorities, closeness and betweenness centrality, groups of nodes (cliques, cores, components and k-components), clustering and clustering coefficients, reciprocity and similarity, structural and other types of equivalence, homophily and types of assortative mixing. Testing Hypotheses: the role of hypotheses in the scientific method, testing hypotheses in network analysis, permutation tests, dyadic hypotheses.
Measures and Metrics, Networks: small-world effects, degree distribution, power laws and scale-free networks, visualisation and properties of power-law distributions, local-clustering coefficient, cohesion, reciprocity, transitivity and the clustering coefficient, triad census, centralisation and core-periphery indices, centrality, random graphs, means on edges and degree, degree distribution, giant and small component(s), locally tree-like networks. Network Visualisation: the importance of network visualisation, graph-layout algorithms, embedding node attributes, node filtering, visualising ego networks, embedding tie characteristics, tie strengths, visualising network change. Handling Large Networks: reducing the size of the problem, eliminating edges, pruning nodes, divide and conquer, aggregation, sampling, small-world and scale-free networks.
Students with specific learning disorders (SLD) or temporary/permanent disabilities should contact the appropriate University office (https://site.unibo.it/studenti-con-disabilita-e-dsa/en) immediately and agree with the teacher the most effective strategies for attending the lectures and preparing for the exam.

Modalità d'esame

The exam’s hand-in consists of a report: a 5000-word PDF done by a group of 3–5 students, detailing the context, the problem/motivation, the data, the measures, and the results of the project that the students performed.
The report is the artefact evaluated for the exam and it is an essential tool for the students to check that they considered and reported on all the important aspects of their project study. The clear presentation/explanation of those aspects also forms the weighted partition that guides the grading, as listed below:
context, problem(s), motivation — 20% dataset(s) and source(s), validity and reliability, applied measure/s and its/their justification, possible hypotheses and tests, results — 60% interpretation of the overall results, critique (brief) — 20%
Please, refer to the website of the teacher for a more detailed exam description.
Students with specific learning disorders (SLD) or temporary/permanent disabilities should contact the appropriate University office (https://site.unibo.it/studenti-con-disabilita-e-dsa/en ) in advance. The office will be responsible for proposing adaptations to interested students. Such adaptations must be submitted to the teacher for approval at least 15 days before the exam session. The teacher will also evaluate the adaptations regarding the training objectives of teaching.

Testi di riferimento

Lecture Notes, Research Papers, and datasets provided by the teacher.
Main references:
Newman, M. (2018). Networks. Oxford university press. Recommended chapters: 1 (+ one or more among 2, 3, 4, 5), 6, 7, 10, 11.
Borgatti, S. P., Everett, M. G., & Johnson, J. C. (2018). Analyzing social networks. Sage. Recommended chapters: 1–8.
Additional references:
Wasserman, S., & Faust, K. (1994). Social network analysis: Methods and applications (Vol. 8). Cambridge university press.
Watts, D. J. (2004). Six degrees: The science of a connected age. WW Norton & Company.
Koch, R., & Lockwood, G. (2011). Superconnect: Harnessing the power of networks and the strength of weak links. Random House Digital, Inc..
Barabasi, A. L. (2014). Linked-how Everything is Connected to Everything Else and what it Means F (pp. 1-1). Perseus Books Group.

Codice insegnamento 90730

User Experience Design 2° anno · 2° semestre · 6 CFU · INF/01 · 0 file

At the end of the course, the student is able to design, implement and evaluate the quality of the interaction with software systems with respect to the dimensions of practicality, experience, affection, meaning and…

Scheda dell'insegnamento

Obiettivi formativi

At the end of the course, the student is able to design, implement and evaluate the quality of the interaction with software systems with respect to the dimensions of practicality, experience, affection, meaning and value that they may have on the target audience. The student is able to focus the functional analysis of the software on the characteristics and needs of the target audience, to drive the development process so as to guarantee a constant connection between the technical and implementation features and the expectation of the audience, and to evaluate whether and according to which metrics a software system satisfies these expectations.

Programma

Teaching will be mostly in English (some explanations will be repeated in Italian if needed and when asked). The exam will be allowed in both Italian and English. The course content is divided in distinct parts:
Background: The evolution of the discipline from Human Computer Interaction to User Experience Design. A description of its scope: the human, the computer, and their interaction. Usability analysis and design: A systematic discussion of the techniques and standards for the management of the process of user experience design, with particular attention to the phases of usability analysis (with and without the participation of users) and the user- and goal-oriented usability design methodologies. Guidelines, patterns and methods for usability design: A discussion, with historical aspects, of the framework on which the concrete aspects of usability design is based. we will also give strong attention to the problem of usability for web applications and mobile apps. Applications of User Experience Design to complex systems (e.g. AI Systems): short module reserved to students in Artificial Intelligence, optional for the other students.
Students with specific learning disorders (SLD) or temporary/permanent disabilities should contact the appropriate University office ( https://site.unibo.it/studenti-con-disabilita-e-dsa/en ) immediately and agree with the teacher the most effective strategies for attending the lectures and preparing for the exam.

Modalità d'esame

The assessment is based on the evaluation of a project to be carried out individually or in a team of 2-3 people plus a written test at the end of the course. Foreign students may want to approach the teacher and agree on a project customized to their needs and interests.
The final score is in the range 0 to 30.
Students with specific learning disorders (SLD) or temporary/permanent disabilities should contact the appropriate University office (https://site.unibo.it/studenti-con-disabilita-e-dsa/en ) in advance. The office will be responsible for proposing adaptations to interested students. Such adaptations must be submitted to the teacher for approval at least 15 days before the exam session. The teacher will also evaluate the adaptations regarding the training objectives of teaching.

Testi di riferimento

Parts of the course are based on:
Human Computer Interaction, Alan Dix, Janet E. Finlay, Gregory D. Abowd, Russell Beale. Prentice Hall; ISBN: 978-0132390484 The Design of Everyday Things , Donald A. Norman, MIT Print, January 2014, ISBN: 978-0262525671 Elements of User Experience,The: User-Centered Design for the Web and Beyond, 2nd Edition, Jesse James Garrett, New Riders, 2011, ISBN: 978-0321683687

Codice insegnamento 91264

95631 MACHINE LEARNING AND DATA MINING 1° semestre · 6 CFU · ING-INF/05 · 0 file
AGENTIC AI SYSTEMS M - Not available for the year 2025/2026 2° semestre · 8 CFU · ING-INF/05 · 0 file
Architecture and Platforms for Artificial Intelligence - Not available for the year 2025/2026 1° semestre · 6 CFU · INF/01 · 0 file
Artificial Intelligence and Robotics - Not available for the year 2025/2026 2° semestre · 6 CFU · ING-INF/05 · 0 file
Artificial Intelligence for Medicine M - Not available for the year 2025/2026 2° semestre · 6 CFU · ING-INF/06 · 0 file
Artificial Intelligence in Industry - Not available for the year 2025/2026 1° semestre · 6 CFU · ING-INF/05 · 0 file
Big Data Analytics and Text Mining - Not available for the year 2025/2026 1° semestre · 6 CFU · ING-INF/05 · 0 file
Blockchain and Cryptocurrencies - Not available for the year 2025/2026 1° semestre · 6 CFU · INF/01 · 0 file
Computational Ethics - Not available for the year 2025/2026 2° semestre · 4 CFU · IUS/20 · 0 file
Cryptography - Not available for the year 2025/2026 1° semestre · 6 CFU · INF/01 · 0 file
Cybersecurity - Not available for the year 2025/2026 1° semestre · 6 CFU · INF/01 · 0 file
Distributed Autonomous Systems M - Not available for the year 2025/2026 2° semestre · 6 CFU · ING-INF/04 · 0 file
Ethics in Artificial Intelligence - Not available for the year 2025/2026 2° semestre · 6 CFU · IUS/20 · 0 file
Expert Systems - Not available for the year 2025/2026 2° semestre · 6 CFU · INF/01 · 0 file
Final Examination - Not available for the year 2025/2026 6 CFU · 0 file
Final Examination - Not available for the year 2025/2026 If you select this activity, it means that you intend to write a thesis for which your continuous presence (in Unibo premises or at external companies/institutions) is NOT requested. Annuale · 24 CFU · 0 file
INTRODUCTION TO QUANTUM COMPUTING - Not available for the year 2025/2026 2° semestre · 6 CFU · INF/01 · 0 file
Internet of Things - Not available for the year 2025/2026 2° semestre · 6 CFU · INF/01 · 0 file
Internship Abroad for Preparation of the Final Examination - Not available for the year 2025/2026 If you select this activity, you intend to enter a competition for international mobility (e.g. Thesis Abroad, Erasmus+, etc.) or to start an internship by a 1° semestre · 18 CFU · 0 file
Internship for Preparation for the Final Examination - Not available for the year 2025/2026 If you select this activity, you intend to start an internship by applying on SOL – Internship (to know more go on your degree course’s website > homepage > studyi 1° semestre · 18 CFU · 0 file
Knowledge Engineering - Not available for the year 2025/2026 2° semestre · 6 CFU · INF/01 · 0 file
Laboratory of Business Plan - Not available for the year 2025/2026 1° semestre · 3 CFU · 0 file
Machine Learning for Computer Vision - Not available for the year 2025/2026 1° semestre · 6 CFU · ING-INF/05 · 0 file
Multi-Agent Systems - Not available for the year 2025/2026 2° semestre · 6 CFU · ING-INF/05 · 0 file
Multimedia Data Management M - Not available for the year 2025/2026 2° semestre · 6 CFU · ING-INF/05 · 0 file
Natural Language Processing - Not available for the year 2025/2026 1° semestre · 6 CFU · ING-INF/05 · 0 file
PROJECT WORK IN SIMULATION - Not available for the year 2025/2026 1° semestre · 3 CFU · 0 file
Preparation for the Final Examination Abroad - Not available for the year 2025/2026 If you select this activity, you intend to enter a competition for international mobility (e.g. Thesis Abroad, Erasmus+, etc.). You will agree with your thesis supervisor 1° semestre · 18 CFU · 0 file
Project Management and Soft Skills M - Not available for the year 2025/2026 2° semestre · 3 CFU · 0 file
Project Work in Architectures and Platforms for Artificial Intelligence - Not available for the year 2025/2026 1° semestre · 3 CFU · 0 file
Project Work in Artificial Intelligence and Robotics - Not available for the year 2025/2026 1° semestre · 3 CFU · 0 file
Project Work in Artificial Intelligence in Industry - Not available for the year 2025/2026 1° semestre · 3 CFU · 0 file
Project Work in Big Data Analytics and Text Mining - Not available for the year 2025/2026 1° semestre · 3 CFU · 0 file
Project Work in Combinatorial Optimization - Not available for the year 2025/2026 1° semestre · 3 CFU · 0 file
Project Work in Deep Learning - Not available for the year 2025/2026 1° semestre · 3 CFU · 0 file
Project Work in Fundamentals of Artificial Intelligence and Knowledge Representation - Not available for the year 2025/2026 1° semestre · 3 CFU · 0 file
Project Work in Image Processing and Computer Vision - Not available for the year 2025/2026 1° semestre · 3 CFU · 0 file
Project Work in Internet of Things - Not available for the year 2025/2026 1° semestre · 3 CFU · 0 file
Project Work in Knowledge Engineering - Not available for the year 2025/2026 1° semestre · 3 CFU · 0 file
Project Work in Languages and Algorithms for Artificial Intelligence - Not available for the year 2025/2026 1° semestre · 3 CFU · 0 file
Project Work in Machine Learning and Data Mining - Not available for the year 2025/2026 1° semestre · 3 CFU · 0 file
Project Work in Machine Learning for Computer Vision - Not available for the year 2025/2026 1° semestre · 3 CFU · 0 file
Project Work in Multi-Agent Systems - Not available for the year 2025/2026 1° semestre · 3 CFU · 0 file
Project Work in Multimedia Data Management M - Not available for the year 2025/2026 1° semestre · 3 CFU · 0 file
Project Work in Natural Language Processing - Not available for the year 2025/2026 1° semestre · 3 CFU · 0 file
Project Work in User Experience Design - Not available for the year 2025/2026 2° semestre · 3 CFU · 0 file
SIMULATION - Not available for the year 2025/2026 1° semestre · 6 CFU · INF/01 · 0 file
Scalable and Reliable Services M - Not available for the year 2025/2026 2° semestre · 8 CFU · ING-INF/05 · 0 file
Social Network Analysis - Not available for the year 2025/2026 1° semestre · 6 CFU · INF/01 · 0 file
User Experience Design - Not available for the year 2025/2026 2° semestre · 6 CFU · INF/01 · 0 file

Recensioni del corso

Studi qui? Accedi per lasciare la tua recensione e aiutare altri studenti a scegliere.

★

Nessuna recensione per ora — e la prima è la più preziosa. Condividi la tua esperienza e orienta le future matricole.