Machine learning is a scientific discipline that deals with the design and development of algorithms that allow computer behaviors to evolve based on empirical data, such as databases or sensor data. A major focus of machine learning research is to make the machine able to recognize and learn complex patterns and make intelligent decisions based on the captured data; the difficulty lies in the fact that the set of all the possible behaviors considering all the possible entries is too complex to describe it by using programming languages. The course will focus on understanding important concepts in machine learning and present the main paradigms and methods that form the basis of modern machine learning. This involves the specific study of learning algorithms as well as the empirical experimentation of algorithms. This course is also an introduction to deep learning, a branch of machine learning concerned with the development and application of modern neural networks. Deep learning algorithms extract layered high-level representations of data in a way that maximizes performance on a given task. It covers a range of topics from basic neural networks, convolutional and recurrent network structures, deep unsupervised and reinforcement learning, LSTM, and applications to problem domains like speech recognition and computer vision.

Temps présentiel : 35 heures

Charge de travail étudiant : 65 heures

Méthode(s) d'évaluation : Examen final, Projets, Travaux pratiques