Description

This course gives an overview of generative deep learning models with a focus on those developed for images. Practical exercises will give the knowledge required to implement them using public datasets. The basics of density estimation will be covered through the early (classical) generative models. Deep models using variational and adversarial approaches will then be discussed, and specific models such as variational auto encoders (VAEs) and generative adversarial networks (GANs) will be introduced. Methods for evaluating generative models will be presented and their limitations discussed. This will lead to tackling advanced generative models to achieve image translation (CycleGAN), and conditional and controllable generation. 

Compétences requises

- Knowledge of python and tensorflow
- Machine learning experience
 - Deep learning experience

Contacts

Responsable(s) de l'enseignement

• Thomas Lampert

MCC

Les épreuves indiquées respectent et appliquent le règlement de votre formation, disponible dans l'onglet Documents de la description de la formation.

Régime d'évaluation

ECI (Évaluation continue intégrale)

Coefficient

3.0

Évaluation initiale / Session principale - Épreuves