- 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 - Hands-on experience on state of the art deep learning algorithms

Probability; programming in python

- 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. - Basics of learning theory - Perceptron. - Artificial Neural Networks. - Support Vector Machines. - Kernel functions. - Active learning - Convolutional Neural Networks. - Optimization and regularization techniques - Visualizations - Generative Adversarial Networks - Recurrent Neural Networks. - Domain adaptation and generalization - Reinforcement 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.

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

Lecture slides; Lab exercises; Video lectures (current year); Student collaboration tools;

Exam: Compulsory oral exam; Group project;

The exam will consist of: 1) 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. 2) the presentation of a paper on a topic related to the group project assigned during the course, with a Q&A session aiming at evaluating the level of understanding of the paper by each component of the group. The presentation of the paper will be done in groups during the third part of the course (reading group). Students that should not be able to make the presentation during the reading group sessions will be assigned a paper to present during the oral exam. 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) for both the paper presentation and the project work. The score for the group work will be maximum 16, with up to 8 points for the project work and up to 8 points for the Q&A session during the project presentation. The points for the project work will be assigned to the whole group, while the points for the Q&A will be assigned individually. The score for the paper presentation will be maximum 16, with up to 8 points for the paper presentation and up to 8 points for the Q&A session following the paper presentation. The points for the paper presentation will be assigned to the whole group, while the points for the Q&A will be assigned individually. Students that will receive an overall score of 32 will be eligible for a 'cum laude' grade.

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.