Caricamento in corso...

01VIATD, 01VIAMY

A.A. 2024/25

Course Language

Inglese

Degree programme(s)

Master of science-level of the Bologna process in Digital Skills For Sustainable Societal Transitions - Torino

Master of science-level of the Bologna process in Geografia E Scienze Territoriali - Torino

Course structure

Teaching | Hours |
---|---|

Lezioni | 27 |

Esercitazioni in aula | 12 |

Esercitazioni in laboratorio | 21 |

Tutoraggio | 40 |

Lecturers

Teacher | Status | SSD | h.Les | h.Ex | h.Lab | h.Tut | Years teaching |
---|---|---|---|---|---|---|---|

Urgese Gianvito | Professore Associato | IINF-05/A | 27 | 12 | 0 | 0 | 4 |

Co-lectures

Espandi

Riduci

Riduci

Teacher | Status | SSD | h.Les | h.Ex | h.Lab | h.Tut |
---|---|---|---|---|---|---|

Fra Vittorio | Ricercatore L240/10 | IINF-05/A | 0 | 0 | 21 | 0 |

Context

SSD | CFU | Activities | Area context |
---|---|---|---|

ING-INF/05 | 6 | B - Caratterizzanti | Tecnologie dell'informatica |

2024/25

This course has a threefold objective:
1) to introduce to the student to the 'cultural' and technological issues related to AI and machine learning (ML)
2) to teach the use of machine learning techniques as a way to solve real problems
3) to gain practice implementing AI and ML algorithms and getting them to work for practical field of application

The aim of this course is threefold:
1) introduce students to the cultural and technological issues related to AI and Machine Learning (ML)
2) teach the use of ML techniques to solve real-world problems
3) Gain experience in implementing AI and ML algorithms and getting them to work in real-world applications.

The student must acquire three fundamental types of knowledge:
1) the understanding of basics concepts (theory and models) of AI and ML
2) the ability to solve concrete problems applying ML algorithms using interactive frameworks and SW libraries
3) the ability to modify and adapt template ML algorithms for a new purpose
These skills will be applied to the solution of practical problems.

The student must acquire three basic types of knowledge:
1) an understanding of the basic concepts (theory and models) of AI and ML
2) the ability to solve concrete problems by applying ML algorithms using interactive frameworks and SW libraries
3) the ability to modify and adapt templates of ML algorithms for new purposes.
These skills will be applied to solve practical problems.

No special prerequirements are expected except some basics of programming language acquired in the course "Computer programming in Python".

No special prerequisites are expected other than some basic knowledge of the programming language acquired in the "Computer Programming in Python" course.

THEORY [40 HRS]
- Hello AI and ML. We introduce the core idea of teaching a computer to learn models using data without being explicitly programmed.
- Background Concepts, Probability and Linear Algebra Review
- Representation of numerical and non-numerical data
- Linear Regression
- Neural Networks Representation and Learning
- Support Vector Machines
- Unsupervised Learning vs Supervised Learning
- Dimensionality Reduction
- Application Examples
LABS [21 HRS]
- Software Development Framework Tutorial
- Several assignments designed to help you understand how to implement the learning algorithms in practice.

THEORY [39 HRS - 4 CFU]
- We introduce the core idea of teaching a computer to learn models from data without being explicitly programmed.
- Background concepts, review of probability and linear algebra.
- Representation of numerical and non-numerical data.
- Unsupervised vs. supervised learning.
- Regression problems and models.
- Classification Problems and Models:
- Support Vector Machines.
- Decision trees.
- Neural Networks.
- other.
- Dimensionality Reduction.
- Clustering problems and models.
- Introduction to prompt engineering and the use of large language models.
- Dimensionality Reduction.
- Application examples.
LABS [21 HRS - 2 CFU]
- KNIME Software Development Framework Tutorial.
- Exercises and assignment tasks are designed to help students understand how to implement the learning algorithms in practice.

The course includes about 21 hours of lab, in which the topics covered in the classes will be implemented using the development framework.

The course includes approximately 21 hours of lab time where the topics covered in class are implemented using the development framework.

Each week the student will attend 3 hours of lectures and 1.5 hours of exercises and laboratories.
The lessons will be divided into different types:
- Theory: illustration of theoretical topics (models, algorithms) with examples
- Problem solving: analysis of real problems and benchmarks, classroom discussion, design/adaptation of ML techniques to solve real applications
- Practice: illustration of the main ML modules available in the development framework and their demonstration using the PC

Each week the student will attend 3 hours of lectures combined with 1.5 hours of exercises and laboratories.
The lessons are divided into different types
- Theory: illustration of theoretical topics (models, algorithms) with examples.
- Problem solving: analysis of real problems and benchmarks, class discussion, design/adaptation of ML techniques to solve real applications.
- Practical: presentation of the main ML modules available in the development framework and their demonstration on the PC.

- Handouts of class material.
- On-line material with references provided during the course.

- Class material handouts.
- Online material with references provided during the course.
[1] Andriy Burkov 2019. The Hundred-Page Machine Learning Book.
[2] Stuart Russell and Peter Norvig 2020. Artificial Intelligence: A Modern Approach. Pearson Education (US)
[3] Christopher M. Bishop. 2006. Pattern Recognition and Machine Learning (Information Science and Statistics). Springer-Verlag, Berlin, Heidelberg.

Slides; Esercizi risolti; Esercitazioni di laboratorio;

Lecture slides; Exercise with solutions ; Lab exercises;

...
The exam will consist of two parts:
1) A set of assignments addressing specific ML tasks to be developed during the course. For each assignment, instructors will provide a dataset and the students will have to develop analysis pipelines to solve the assigned problem (based on the topics presented during lectures and labs). Then, students should write a technical report detailing the employed methodology and a critical analysis of the obtained results. Both the designed pipeline and the report will be submitted by students to the instructor for evaluation.
2) A written test that aims at assessing the student's knowledge of the theoretical aspects of the course (through practical exercises and open-answer questions) and the ML design skills (through the designing of analysis pipelines that implement the solution of a practical problem for which datasets are provided).
The exam will assess the developed skills of the candidate to solve specific problems by applying the knowledge acquired during the course in the design of ML pipelines of data analysis.
The duration of the written test is 1.5 hours and it is a closed book test.
The maximum score for the written test is 30 cum laude.
During the discussion of the results of the written test, the instructor can request a supplementary oral test that can cover the whole course program and is meant to assess and elaborate the student's skills.

Gli studenti e le studentesse con disabilità o con Disturbi Specifici di Apprendimento (DSA), oltre alla segnalazione tramite procedura informatizzata, sono invitati a comunicare anche direttamente al/la docente titolare dell'insegnamento, con un preavviso non inferiore ad una settimana dall'avvio della sessione d'esame, gli strumenti compensativi concordati con l'Unità Special Needs, al fine di permettere al/la docente la declinazione più idonea in riferimento alla specifica tipologia di esame.

The exam consists of two parts:
1) A series of assignments dealing with specific ML problems to be developed during the course. For each assignment, the lecturers will provide a dataset and the students will have to develop analysis pipelines to solve the assigned problem (based on topics presented in lectures and labs). Students will then write a technical report detailing the methodology used and a critical analysis of the results obtained. Both the designed pipeline and the report will be submitted by the students to the teacher for evaluation.
2) A written exam that aims to assess the students' knowledge of the theoretical aspects of the course (through practical exercises and open-ended questions) and the ML design skills (through the design of analysis pipelines that implement the solution of a practical problem for which datasets are provided).
The exam assesses the candidate's ability to solve specific problems by applying the knowledge acquired during the course to the design of ML data analysis pipelines.
The duration of the written exam is 2 hours and it is a closed-book exam.
The maximum score for the written exam is 30 cum laude.
During the discussion of the results of the written test, the teacher may request a supplementary oral test, which may cover the entire course programme and is designed to assess and develop the student's skills.

In addition to the message sent by the online system, students with disabilities or Specific Learning Disorders (SLD) are invited to directly inform the professor in charge of the course about the special arrangements for the exam that have been agreed with the Special Needs Unit. The professor has to be informed at least one week before the beginning of the examination session in order to provide students with the most suitable arrangements for each specific type of exam.