Thierry Artières

Implicit Regularization in Deep Tensor Factorization

Attempts of studying implicit regularization associated to gradient descent (GD) have identified matrix completion as a suitable test-bed. Late findings suggest that this phenomenon cannot be...

Mapping individual differences in cortical architecture using multi-view representation learning

In neuroscience, understanding inter-individual differences has recently emerged as a major challenge, for which functional magnetic resonance imaging (fMRI) has proven invaluable. For this,...

Multi-View Data Generation Without View Supervision

The development of high-dimensional generative models has recently gained a great surge of interest with the introduction of variational auto-encoders and generative adversarial neural networks....

Learning States Representations in POMDP

We propose to deal with sequential processes where only partial observations are available by learning a latent representation space on which policies may be accurately learned.

Classification and Tracking of Hypermedia Navigation Patterns

Apprentissage de comportements utilisateurs de produits hypermédias

Apprentissage d'une hiérarchie de concepts pour la conception de modèles de domaine d'hypermédias

Optimisation du Primal pour les SVM

Un système d'aide à la navigation dans des hypermédias

Sélection de modèles par des méthodes à noyaux pour la classification de données séquentielles

Champs de Markov conditionnels pour le traitement de séquences

Multi-View Data Generation Without View Supervision

Unsupervised Object Segmentation by Redrawing

Robust Bloom Filters for Large MultiLabel Classification Tasks

A Model-Based Approach to Sequence Clustering

Patch Learning for Incremental Classifier Design

Polynomial Conditional Random Fields for Signal Processing

Joint Syntactic and Semantic Analysis with a Multitask Deep Learning Framework for Spoken Language Understanding