UE Advanced Artificial Intelligence : Advanced Machine Learn

Code de l'ECUE : KMUAAIU

Ce cours appartient à CHOIX Mineures DS4H - M1 LEA RFI qui contient 44 ECUE

Structure

EUR DS4H

Domaine disciplinaire

Informatique , Mathématiques

Lieu d'enseignement

Campus SophiaTech Les Lucioles , Campus Valrose

Niveau du cours

Master 1 , Master 2

Semestre

Semestre impair

Langue

Anglais

PRESENTATION

This course will develop an introduction to ML, by reviewing the fundamental principles and methods. Broadly speaking, Machine learning (ML) is the scientific field aiming at building models and inferring knowledge by applying algorithms to data. Therefore, the process involves the (statistical) analysis of data, and the design of models, possibly predictive. During this course, we will be more interested in the framework of use of the different methods rather than their mathematical foundations or their effective computer implementations.

This minor is open to students from the DS4H, and SPECTRUM graduate schools. According to their cursus, each student have different need and their level could be quiet different. So each session will be divided in two modules :

One lecture for all students during approximately 1h to 1h30 ;
One tutorial during approximately 2 hours with 2 separate groups adapted to 2 differents levels : Python (advanced), Python (beginner).

Responsable(s) du cours

, Michel Riveill

Présentiel

12h de travaux dirigés

Distanciel

12h de cours magistral

PREREQUIS

Avant le début du cours, je dois ...

Scientific Bachelor, Python programming, Prerequisites and main concepts of Minor AI Introduction

OBJECTIFS

A la fin de ce cours, je devrais être capable de...

o Know the principles of Deep Learning (neural network) o Know how to build models based on neural networks to process structured data, images or text

CONTENU

Session 1

- Course goals and outline ((Michel Riveill)

- An introduction to Natural Language Processing (Michel Riveill)
Session 2

Deep learning – General principles (Michel Riveill)
Session 3

Deep learning - Multi-Layers perceptron (Michel Riveill)
Session 4

Deep learning - Recommender Systems (Michel Riveill)
Session 5

Deep learning - Recurrent Neural Network (Michel Riveill)
Session 6

Deep learning - Convolutional Neural Network (Diane Lingrand)
Session 7

Deep learning – Model Explainability (Diane Lingrand)
Session 8

Deep learning - Reinforcement Learning (Diane Lingrand)

Accéder au Syllabus complet (Authentification requise)

Important

Ce syllabus n’a aucune valeur contractuelle. Son contenu est susceptible d’évoluer en cours d’année : soyez attentifs aux dernières modifications.