01USPLO

A.A. 2022/23

Course Language

Inglese

Course degree

Master of science-level of the Bologna process in Automotive Engineering (Ingegneria Dell'Autoveicolo) - Torino

Course structure

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

Lezioni | 42 |

Esercitazioni in aula | 18 |

Teachers

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

Tommasi Tatiana | Professore Associato | ING-INF/05 | 32 | 18 | 0 | 0 | 2 |

Teaching assistant

Context

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

ING-INF/05 | 6 | F - Altre attivitą (art. 10) | Altre conoscenze utili per l'inserimento nel mondo del lavoro |

2022/23

The course addresses the core issues in modern artificial intelligence and machine learning, with a special focus on advanced algorithms and theory of shallow and deep machine learning. Lab activities will equip students with first-hand experience on modern optimization methods and programming framework most used in advance research and companies as of today, and to have first hand experiences on the properties of such algorithms on specific case studies.

The course addresses the core issues in modern artificial intelligence and machine learning, with a special focus on advanced algorithms and theory of shallow and deep machine learning. Lab activities will equip students with first-hand experience on modern optimization methods and programming framework most used in advance research and companies as of today, and to have first hand experiences on the properties of such algorithms on specific case studies.

- Knowledge of the main characteristics of artificial intelligence: historical overview and modern definition
- Knowledge of how to formalize a learning problem from the mathematical foundations of the optimization objectives to the composition of a deep architecture
- Knowledge of the main characteristics of modern deep learning techniques with practical engineering tricks for end-to-end training and fine-tuning the networks
- Basic knowledge about how to deal with research questions, how to organize a project and prepare a scientific conference report

- Knowledge of the main characteristics of artificial intelligence: historical overview and modern definition
- Knowledge of how to formalize a learning problem from the mathematical foundations of the optimization objectives to the composition of a deep architecture
- Knowledge of the main characteristics of modern deep learning techniques with practical engineering tricks for end-to-end training and fine-tuning the networks
- Basic knowledge about how to deal with research questions, how to organize a project and prepare a scientific conference report

- Linear Algebra
- Probability theory concepts
- Basic concepts of decision theory (model optimization)
- Python: Basic elements

- Linear Algebra
- Probability theory concepts
- Basic concepts of decision theory (model optimization)
- Python: Basic elements

- Artificial Intelligence: historical definition, brief overview, modern definition and current role of machine and deep learning
- Overview of fundamental knowledge of probability
- Overview of decision theory: loss, risk, Probably Approximately Correct (PAC) Learning
- Perceptron - Support Vector Machines beyond classification
- Artificial Neural Networks
- Convolutional Neural Networks basic algorithms: Backpropagation and Stochastic Gradient Descent
- Training a CNN (data preprocessing, weight initialization and hyperparameter optimization)
- Visualizing and Understanding the CNN inner working
- Multi-Task and Structured Output Learning (Semantic Segmentation and Detection)
- Unsupervised and Metric Learning (Siamese networks and Contrastive Learning for Retrieval)
- Generative Networks (Autoencoders and GANs) - Recurrent Neural Networks
- Learning with few samples and across domains
- Active and Incremental learning
- Basic concepts and networks for Reinforcement Learning

- Artificial Intelligence: historical definition, brief overview, modern definition and current role of machine and deep learning
- Overview of fundamental knowledge of probability
- Overview of decision theory: loss, risk, Probably Approximately Correct (PAC) Learning
- Perceptron - Support Vector Machines beyond classification
- Artificial Neural Networks
- Convolutional Neural Networks basic algorithms: Backpropagation and Stochastic Gradient Descent
- Training a CNN (data preprocessing, weight initialization and hyperparameter optimization)
- Visualizing and Understanding the CNN inner working
- Multi-Task and Structured Output Learning (Semantic Segmentation and Detection)
- Unsupervised and Metric Learning (Siamese networks and Contrastive Learning for Retrieval)
- Generative Networks (Autoencoders and GANs) - Recurrent Neural Networks
- Learning with few samples and across domains
- Active and Incremental learning
- Basic concepts and networks for Reinforcement Learning

- 48 hours of lectures (theory section)
- 12 hours of 'laboratory' exercises (practical section)

- 48 hours of lectures (theory section)
- 12 hours of 'laboratory' exercises (practical section)

Slides + State of the art deep learning top conference and journal papers.
Optional - specific pointers to chapters of the following books will be indicated during the lectures.
Artificial Intelligence: A Modern Approach S. Russell, P.Norvig
Deep Learning by I. Goodfellow, Y. Bengio, A. Courville.
Understanding Machine Learning: From Theory to Algorithms by Shai Shalev-Shwartz and Shai Ben-David
Machine Learning: a Probabilistic Perspective by Kevin P. Murphy
The Elements of Statistical Learning, T. Hastie, R. Tibshirani, and J. Friedman
Pattern Recognition and Machine Learning, Christopher M. Bishop
Machine Learning, Tom M. Mitchell A Course in Machine Learning, Hal Daumé III
Neural Networks - a Systematic Introduction, Raul Rojas

Slides + State of the art deep learning top conference and journal papers.
Optional - specific pointers to chapters of the following books will be indicated during the lectures.
Artificial Intelligence: A Modern Approach S. Russell, P.Norvig
Deep Learning by I. Goodfellow, Y. Bengio, A. Courville.
Understanding Machine Learning: From Theory to Algorithms by Shai Shalev-Shwartz and Shai Ben-David
Machine Learning: a Probabilistic Perspective by Kevin P. Murphy
The Elements of Statistical Learning, T. Hastie, R. Tibshirani, and J. Friedman
Pattern Recognition and Machine Learning, Christopher M. Bishop
Machine Learning, Tom M. Mitchell A Course in Machine Learning, Hal Daumé III
Neural Networks - a Systematic Introduction, Raul Rojas

Gli studenti e le studentesse con disabilitą 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'Unitą Special Needs, al fine di permettere al/la docente la declinazione pił idonea in riferimento alla specifica tipologia di esame.

- group project (50%): the students are asked to test pre-existing code of state of the art deep learning models and to understand its functioning. Each group prepares slides and organize a short presentation to discuss the literature related to the chosen project topic and report on the observed behavior of the models.
- individual evaluation (50%): questions on the theory and laboratory (exercises) part of the course program.

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.

© Politecnico di Torino

Corso Duca degli Abruzzi, 24 - 10129 Torino, ITALY

Corso Duca degli Abruzzi, 24 - 10129 Torino, ITALY