Modèles génératifs pour l’image
The goal of this course is to present and study generative models that can be used for various image generation tasks. The first part of the course will focus on models relying on an adversarial framework, namely Generative Adversarial Networks
Deformable models and geodesic methods for image analysis
A large overview of methods and algorithms of deformable models for image segmentation, illustrated by concrete applications Presentation : here
Imagerie fonctionnelle cérébrale et interface cerveau machine
Ce cours porte sur l’imagerie cérébrale fonctionnelle et son application à la réalisation d’interfaces cerveau-ordinateur à partir de deux techniques non-invasives qui permettent l’activité cérébrale. la M/EEG mesure le champ électromagnétique créé par les courants électriques corticaux ; l’IRM fonctionnelle
Nuages de Points et Modélisation 3D (NPM3D)
Il s’agit de faire un panorama des concepts et techniques d’acquisition, de traitement et de visualisation des nuages de points 3D, et de leurs fondements mathématiques et algorithmiques. Présentation : Cliquez ici
Audio signal processing – Time-frequency analysis
Initiation to several signal processing techniques specific to audio processing
Remote sensing data: from sensor to large-scale geospatial data exploitation
Provide a good understanding of earth observation systems and their mathematical modeling (optic and SAR satellite sensors), with a focus on data processing for elevation recovery (stereo-vision and SAR interferometry) and time series analysis. Handling of real images from space
Biostatistics
The course aims at introducing both concepts and methods used in clinical (or medical) research. It is integrated to the health science theme of the master program.The course will both emphasize the principles and concepts underlying the different goals of
Deep Learning
With the increase of computational power and amounts of available data, but also with the development of novel training algorithms and new whole approaches, many breakthroughs occurred over the few last years in Deep Learning for object and spoken language
Advanced learning for text and graph data ALTEGRAD
The ALTEGRAD course ( 28 hours) aims at providing an overview of state-of-the-art ML and AI methods for text and graph data with a significant focus on applications. Each session will comprise two hours of lecture followed by two hours
Introduction to statistical learning
The course presents the mathematical foundations for supervised learning.