01TXFSM, 01TXFNG

A.A. 2021/22

2021/22

Machine learning and Deep learning

The course is offered on the II semester of the I year. The course is taught in English. The course addresses the core issues in machine learning, with a special focus on algorithms and theory of statistical machine learning, and modern techniques for deep learning. Lab activities will quip 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.

Machine learning and Deep learning

The course is offered on the II semester of the I year. The course is taught in English. The course addresses the core issues in machine learning, with a special focus on algorithms and theory of statistical machine learning, and modern techniques for deep learning. Lab activities will quip 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.

Machine learning and Deep learning

- Knowledge of the main characteristics of artificial Intelligence: historical overview and modern definition; role of Machine and deep learning - Knowledge of the main characteristics of Statistical Machine Learning: theory and algorithms - Knowledge of the main characteristics of Artificial Neural Networks - Knowledge of the main characteristics of modern Deep Learning techniques

Machine learning and Deep learning

- Knowledge of the main characteristics of artificial Intelligence: historical overview and modern definition; role of Machine and deep learning - Knowledge of the main characteristics of Statistical Machine Learning: theory and algorithms - Knowledge of the main characteristics of Artificial Neural Networks - Knowledge of the main characteristics of modern Deep Learning techniques

Machine learning and Deep learning

Probability

Machine learning and Deep learning

Probability

Machine learning and Deep learning

- Artificial Intelligence: historical definition, brief overview, modern definition and current role of machine and deep learning. - Overview of fundamental knowledge of probability. - Generative and discriminative methods. - Perceptron. - Artificial Neural Networks. - Support Vector Machines. - Kernel functions. - Active learning - Convolutional Neural Networks. - Stochastic Gradiant Descent. - Batch Normalization. - Generative Adversarial Networks - Recurrent Neural Networks. - Learning theory. - Data bias - Learning to learn

Machine learning and Deep learning

- Artificial Intelligence: historical definition, brief overview, modern definition and current role of machine and deep learning. - Overview of fundamental knowledge of probability. - Generative and discriminative methods. - Perceptron. - Artificial Neural Networks. - Support Vector Machines. - Kernel functions. - Active learning - Convolutional Neural Networks. - Stochastic Gradiant Descent. - Batch Normalization. - Generative Adversarial Networks - Recurrent Neural Networks. - Learning theory. - Data bias - Learning to learn

Machine learning and Deep learning

Machine learning and Deep learning

Machine learning and Deep learning

The course includes practices on the lecture topics and laboratory sessions during which the students will form team and work on specific projects assigned to them. Laboratory sessions allow experimental activities on the most widespread commercial and open-source products.

Machine learning and Deep learning

The course includes practices on the lecture topics and laboratory sessions during which the students will form team and work on specific projects assigned to them. Laboratory sessions allow experimental activities on the most widespread commercial and open-source products.

Machine learning and Deep learning

Copies of the slides used during the lectures will be made available. All teaching material is downloadable from the teaching Portal. Reference books: - I. Goodfellow, Y. Bengio, A. Courville. Deep Learning. MIT press. - K. P. Murphy. Machine Learning: a probabilistic perspective. MIT Press

Machine learning and Deep learning

Copies of the slides used during the lectures will be made available. All teaching material is downloadable from the teaching Portal. Reference books: - I. Goodfellow, Y. Bengio, A. Courville. Deep Learning. MIT press. - K. P. Murphy. Machine Learning: a probabilistic perspective. MIT Press

Machine learning and Deep learning

**Modalità di esame:** Prova orale obbligatoria; Elaborato progettuale in gruppo;

Machine learning and Deep learning

The exam includes a mandatory oral part, and the evaluation of the report on the team projects assigned during the course.

Machine learning and Deep learning

**Exam:** Compulsory oral exam; Group project;

Machine learning and Deep learning

The exam will consist of the presentation of the group project assigned during the course, with a Q&A session aiming at evaluating the level of understanding of the work done in the project by each component of the group, and the level of understanding of the course topic's in general. The final grade will be given by an assessment of the group work (50% of the grade) and an assessment of the oral exam (50% of the grade).

Machine learning and Deep learning

**Modalità di esame:** Prova orale obbligatoria; Elaborato progettuale in gruppo;

Machine learning and Deep learning

The exam will consist of a written test, a practical project in group and the presentation and discussion of the project of the group, with a Q&A session

Machine learning and Deep learning

**Exam:** Compulsory oral exam; Group project;

Machine learning and Deep learning

The exam will consist of the presentation of the group project assigned during the course, with a Q&A session aiming at evaluating the level of understanding of the work done in the project by each component of the group, and the level of understanding of the course topic's in general. The final grade will be given by an assessment of the group work (50% of the grade) and an assessment of the oral exam (50% of the grade).

Machine learning and Deep learning

**Modalità di esame:** Prova orale obbligatoria; Elaborato progettuale in gruppo;

Machine learning and Deep learning

The exam will consist of a written test, a practical project in group and the presentation and discussion of the project of the group, with a Q&A session

Machine learning and Deep learning

**Exam:** Compulsory oral exam; Group project;

Machine learning and Deep learning

The exam will consist of the presentation of the group project assigned during the course, with a Q&A session aiming at evaluating the level of understanding of the work done in the project by each component of the group, and the level of understanding of the course topic's in general. The final grade will be given by an assessment of the group work (50% of the grade) and an assessment of the oral exam (50% of the grade).

© Politecnico di Torino

Corso Duca degli Abruzzi, 24 - 10129 Torino, ITALY

Corso Duca degli Abruzzi, 24 - 10129 Torino, ITALY