Designing semantic feature spaces for brain-reading - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

Designing semantic feature spaces for brain-reading

Luepol Pipanmaekaporn
  • Fonction : Auteur
Vincent Guigue
Thierry Artières

Résumé

We focus on a brain-reading task which consists in discovering a word a person is thinking of based on an fMRI image of their brain. Previous studies have demonstrated the feasibility of this brain-reading task through the design of what has been called a semantic space, i.e. a continuous low dimensional space reflecting the similarity between words. So far the best results have been achieved by carefully designing this semantic space by hand which limits the generalization of such a method. We propose to automatically design several semantic spaces from linguistic resources and to combine them in a principled way and achieve results comparable to that of manually built semantic spaces.
Fichier non déposé

Dates et versions

hal-01196369 , version 1 (09-09-2015)

Identifiants

  • HAL Id : hal-01196369 , version 1

Citer

Luepol Pipanmaekaporn, Ludmilla Tajtelbom, Vincent Guigue, Thierry Artières. Designing semantic feature spaces for brain-reading. ESANN 2015 - 23rd European Symposium on Artificial Neural Networks, Apr 2015, Bruges, Belgium. pp.433-438. ⟨hal-01196369⟩
151 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More