02SQING, 01SQIOV

A.A. 2020/21

Course Language

Inglese

Course degree

Master of science-level of the Bologna process in Ingegneria Matematica - Torino

Master of science-level of the Bologna process in Ingegneria Informatica (Computer Engineering) - Torino

Course structure

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

Lezioni | 48 |

Esercitazioni in laboratorio | 12 |

Teachers

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

Tommasi Tatiana | Professore Associato | ING-INF/05 | 28 | 0 | 0 | 0 | 2 |

Teaching assistant

Context

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

ING-INF/05 | 6 | D - A scelta dello studente | A scelta dello studente |

2020/21

The course, optional for the Master degree in computer engineering, is offered on the I semester of the II year. The course is taught in English. 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, optional for the Master degree in computer engineering, is offered on the I semester of the II year. The course is taught in English. 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)
- 16 hours of 'laboratory' exercises (practical section)

- 48 hours of lectures (theory section)
- 16 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

- individual homework reports
- final project
- oral exam on project presentation and on the theory topics presented during lectures

- final group (3 students) project. It consists in reproducing and extending a current state of the art deep learning method. The students will elaborate a pdf report of about 8 pages in ieee paper format and will present the work in a 15 minutes talk during the oral exam.
- oral exam on project presentation (group) and on the theory topics presented during lectures (individual questions).

- individual homework reports
- final project
- written exam on topics presented during lectures

- final group (3 students) project. It consists in reproducing and extending a current state of the art deep learning method. The students will elaborate a pdf report of about 8 pages in ieee paper format.
- 2h written exam on topics presented during lectures. Open-ended questions on theory and exercises.

© Politecnico di Torino

Corso Duca degli Abruzzi, 24 - 10129 Torino, ITALY

Corso Duca degli Abruzzi, 24 - 10129 Torino, ITALY