Détails

Faculté	Faculté des sciences et de médecine
Domaine	Mathématiques
Code	UE-SMA.03413
Langues	Anglais , Français
Type d'enseignement	Cours
Cursus	Bachelor
Semestre(s)	SA-2021

Horaires et salles

Horaire résumé	Lundi 13:15 - 15:00, Hebdomadaire (Semestre d'automne)
Heures par semaine	2

Enseignement

Responsables	Mazza Christian
Enseignants	Mazza Christian
Description	This course aims at presenting and studying mathematically models from statistical learning theory, by focusing on deep learning algorithms in multi-layer neural networks. Applications to artificial intelligence will be provided. We will also present and study the basic probabilistic and statistical models of machine learning by making links with neural nets. A special emphasis will be given to deep learning processes for Boltzmann machines using methods from probability theory, statistics and statistical mechanics.
Objectifs de formation	Topics focus on but are not limited to: Biological neural networks, mathematical models of neural nets, learning algorithms (Hebb rule) for Hopfield neural nets and Boltzmann machines, machine learning and multivariate statistics (discriminant analysis, regression), general statistical learning theory (deterministic and stochastic models, Vapnik-Cervonenkis theory), learning processes in associative memories, perceptron and multi-layer neural nets, stochastic processes for deep learning in Boltzmann machines, thermodynamic extension (statistical mechanics of learning processes),
Commentaire	compte pour Mathématiques appliquées
Softskills	Non
Hors domaine	Non
BeNeFri	Oui
Mobilité	Oui
UniPop	Non

Examen oral - SA-2021, Session d'hiver 2022

Mode d'évaluation

Par note

Examen oral - SP-2022, Session d'été 2022

Mode d'évaluation

Par note

Examen oral - SP-2022, Session d'automne 2022

Mode d'évaluation

Par note