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 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.

- 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

Probability

Class topics - 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. - Learning theory. - Convolutional Neural Networks. - Stochastic Gradiant Descent. - Batch Normalization. - Recurrent Neural Networks.

I. Goodfellow, Y. Bengio, A. Courville. Deep Learning. MIT press. K. P. Murphy. Machine Learning: a probabilistic perspective. MIT Press

Modalità di esame: Prova scritta (in aula); Prova orale obbligatoria;

Exam: Written test; Compulsory oral exam;

... The exam includes a written part, which lasts 2 hours, a mandatory oral part, and the evaluation of the report on the individual practices assigned during the course.

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.