Publications | Jean-Noël Vittaut

TIGTEC: Token Importance Guided TExt Counterfactuals

Counterfactual examples explain a prediction by highlighting changes in an instance that flip the outcome of a classifier. This paper …

Milan Bhan, Jean-Noël Vittaut, Nicolas Chesneau, Marie-Jeanne Lesot

Operator Learning with Neural Fields: Tackling PDEs on General Geometries

Machine learning approaches for solving partial differential equations require learning mappings between function spaces. While …

Louis Serrano, Lise Le Boudec, Armand Kassaï Koupaï, Thomas X Wang, Yuan Yin, Jean-Noël Vittaut, Patrick Gallinari

Operator Learning on Free-Form Geometries

Operator Learning models usually rely on a fixed sampling scheme for training which might limit their ability to generalize to new …

Louis Serrano, Jean-Noël Vittaut, Patrick Gallinari

Enhancing textual counterfactual explanation intelligibility through Counterfactual Feature Importance

Textual counterfactual examples explain a prediction by modifying the tokens of an initial instance in order to flip the outcome of a …

Milan Bhan, Jean-Noël Vittaut, Nicolas Chesneau, Marie-Jeanne Lesot

Recherches en IA explicable dans l'équipe LFI du LIP6

Cet article présente brièvement ces contributions développées dans le cadre de multiples collaborations, en évoquant les tâches …

Christophe Marsala, Isabelle Bloch, Marie-Jeanne Lesot, Sabrina Tollari, Jean-Noël Vittaut

Exploiting Game Decompositions in Monte Carlo Tree Search

In this paper, we propose a variation of the MCTS framework to perform a search in several trees to exploit game decompositions. Our …

Aline Hufschmitt, Jean-Noël Vittaut, Nicolas Jouandeau

Recherche Monte Carlo multi-arbres pour l’exploitation des jeux décomposés

Dans cet article nous présentons une variation de la recherche arborescente Monte Carlo (MCTS) consistant à réaliser une recherche dans …

Aline Hufschmitt, Jean-Noël Vittaut, Nicolas Jouandeau

Statistical GGP Game Decomposition

This paper presents a statistical approach for the decomposition of games in the General Game Playing framework. General game players …

Aline Hufschmitt, Jean-Noël Vittaut, Nicolas Jouandeau

Décomposition des jeux pour le General Game Playing

Dans cet article nous présentons une approche pour la décomposition des jeux généraux décrits en Game Description Language (GDL). Dans …

Aline Hufschmitt, Jean-Noël Vittaut, Nicolas Jouandeau

LeJoueur : un programme de General Game Playing pour les jeux à information incomplète et/ou imparfaite

This thesis is a contribution to the General Game Playing domain (GGP), a problematic of Artificial Intelligence (AI) aiming at …

Jean-Noël Vittaut

A General Approach of Game Description Decomposition for General Game Playing

We present a general approach for the decomposition of games described in the Game Description Language (GDL). In the field of General …

Aline Hufschmitt, Jean-Noël Vittaut, Jean Méhat

Using the MPPA Architecture for UCT Parallelization

We present here a study of the use of a Multi-Purpose Processor Array (MPPA) architecture for the parallelization of the UCT algorithm …

Aline Hufschmitt, Jean Méhat, Jean-Noël Vittaut

MCTS Playouts Parallelization with a MPPA Architecture

We present a study of the use of a Multi-Purpose Processor Array (MPPA) architecture for the parallelization of MCTS algorithms applied …

Aline Hufschmitt, Jean Méhat, Jean-Noël Vittaut

Fast Instantiation of GGP Game Descriptions Using Prolog with Tabling

We present a method to instantiate game descriptions used in General Game Playing with a Prolog interpreter using tabling. …

Jean-Noël Vittaut, Jean Méhat

Efficient Grounding of Game Descriptions with Tabling

We present a method to instantiate game descriptions used in General Game Playing with the tabling engine of a Prolog interpreter. …

Jean-Noël Vittaut, Jean Méhat

Online Adjustment of Tree Search for GGP

We present an adaptive method that enables a General Game Player using Monte-Carlo Tree Search to adapt its use of RAVE to the game it …

Jean Méhat, Jean-Noël Vittaut

Segmented Images Colorization Using Harmony

In the colorization process, artists fill image’s regions with colors following harmony rules. Some region colorizations are more …

Catherine Sauvaget, Stéphane Manuel, Jean-Noël Vittaut, Jordane Suarez, Vincent Boyer

Automated Colorization of Segmented Images Based on Color Harmony

We propose in this paper an automated colorization of segmented images based on a color harmony ruledefined by Itten called the …

Catherine Sauvaget, Jean-Noël Vittaut, Jordane Suarez, Vincent Boyer, Stéphane Manuel

Supervised and Semi-supervised Machine Learning Ranking

We present a Semi-supervised Machine Learning based ranking model which can automatically learn its parameters using a training set of …

Jean-Noël Vittaut, Patrick Gallinari

Machine Learning Ranking for Structured Information Retrieval

We consider the Structured Information Retrieval task which consists in ranking nested textual units according to their relevance for a …

Jean-Noël Vittaut, Patrick Gallinari

Apprentissage d'ordonnancements en recherche d'information structurée

Nous présentons un modèle d’apprentissage pour la Recherche d’Information Structurée qui ajuste automatiquement ses …

Jean-Noël Vittaut, Patrick Gallinari

Machine Learning Ranking and INEX'05

We present a Machine Learning based ranking model which can automatically learn its parameters using a training set of annotated …

Jean-Noël Vittaut, Patrick Gallinari

An Algebra for Structured Queries in Bayesian Networks

We present a system based on a Bayesian Network formalism for structured documents retrieval. The parameters of this model are learned …

Jean-Noël Vittaut, Benjamin Piwowarski, Patrick Gallinari

Structured Multimedia Document Classification

We propose a new statistical model for the classification of structured documents and consider its use for multimedia document …

Ludovic Denoyer, Jean-Noël Vittaut, Patrick Gallinari, Sylvie Brunessaux, Stephan Brunessaux

Learning Classification with Both Labeled and Unlabeled Data

A key difficulty for applying machine learning classification algorithms for many applications is that they require a lot of …

Jean-Noël Vittaut, Massih-Reza Amini, Patrick Gallinari