Main topics


Statistical Machine Learning

Deep Learning and Neural Networks

Artificial Intelligence


Current projects


Sequence modeling, labeling and classification

Design of statistical models for sequence labeling and classification based on Hidden Markov Models, Conditional Random Fields, and variants like Contextual Hidden Markov Models, Hidden Conditional Random Fields, neural extensions of these models etc.

 

 


Extreme Classification

Extreme classification means classification in a very large number of classes (up top millions), either in monolabel or multilabel classification settings. This projet consisted in part in designing new methods for this challenging setting and in organizing international large scale classification challenges (LSHTC series and BioAsQ series).

 

 

 


Budgeted Learning

 

 Budget learning covers various topics. This project aimed at designing classifiers that are economic in the number of features that are required to produce a  decision on an input data.

Multiview Learning

With Mickael Chen and Ludovic Denoyer at LIP6


Multisource Learning

With Qi Wang and Sylvain Takekart (INT)


Adversarial Learning For Animation

With Qi Wang.

We designed synthesis systems for generating motion capture data that matchs some high level  features ( e.g. the emotion with which an motion is performed) using adversarial learning and recurrent neural nets.


Disentangling factors of variations

With Mickael Chen and Ludovic Denoyer at LIP6, UPMC

Disentangling factors of variations aims at learning factors of variations from data. Once learned it allows changing the stye of an input data (e.g. viewpoint for image data) to the style of another image. We have applied such techniques, relying on adversarial learning on images and on motion capture sequences.

 


Deep Learning For Vocal Brain Analysis

With Pascal Belin and Sylvain Takerkart at INT

The project aims at creating a map of the brain areas according to its processing level of input stimuli by comparing cerebral representations with learned representations in a deep neural net.

Deep Learning For High Energy Physics

With Ziyu Guo and Y. Coadou at CPPM


Mixing Deep Learning And Kernels

With Luc Giffon, Stéphane Ayache, Hachem Kadri