Ressource pédagogique : Reconnaissance d’objets, une problématique résolue ? / Has object vision been solved?

The ability of humans to identify and categorize objects in complex natural scenes has long been thought to be beyond the capacities of artificial vision systems. However, recent progress in Deep Learning and Convolutional Neural Networks has demonstrated that simple feed-forward processing arch...
cours / présentation - Date de création : 10-07-2015
Auteur(s) : Simon THORPE
Partagez !

Présentation de: Reconnaissance d’objets, une problématique résolue ? / Has object vision been solved?

Informations pratiques sur cette ressource

Anglais
Type pédagogique : cours / présentation
Niveau : doctorat
Durée d'exécution : 1 heure 25 minutes 45 secondes
Contenu : image en mouvement
Document : video/mp4
Taille : 720.69 Mo
Droits : libre de droits, gratuit
Droits réservés à l'éditeur et aux auteurs. © Inria Bordeaux - Sud-Ouest

Description de la ressource pédagogique

Description (résumé)

The ability of humans to identify and categorize objects in complex natural scenes has long been thought to be beyond the capacities of artificial vision systems. However, recent progress in Deep Learning and Convolutional Neural Networks has demonstrated that simple feed-forward processing architectures composed of less than 10 layers of neurons can achieve human levels of performance in object recognition tasks. It is interesting to note that such processing architectures have a very similar structure to the primate visual system. Could it be that we are close to understanding how our brains recognize stimuli? I will argue that the main problem with the current state of the art in computer vision is that the learning procedures used are totally unrealistic. Essentially, building such a system requires hundreds of millions of training cycles of supervised learning. By contrast, our own visual systems can learn new stimuli in a few tens of presentations. I will suggest that more biologically realistic learning mechanisms based on spike-based processing and Spike Time Dependent Plasticity (STDP) may be much closer to the way our own visual systems operate, and allow our visual systems to learn about objects in the visual world on the basis of experience.

"Domaine(s)" et indice(s) Dewey

  • Intelligence artificielle, réseaux neuronaux, automates cellulaires, vie artificielle (006.3)

Thème(s)

Intervenants, édition et diffusion

Intervenants

Fournisseur(s) de contenus : INRIA (Institut national de recherche en informatique et automatique)

Diffusion

Partagez !

AUTEUR(S)

  • Simon THORPE

EN SAVOIR PLUS

  • Identifiant de la fiche
    23890
  • Identifiant
    oai:canal-u.fr:23890
  • Schéma de la métadonnée
  • Entrepôt d'origine
    Canal-u.fr