Ressource documentaire
| Reconnaissance d’objets, une problématique résolue ? / Has object vision been solved? (en Anglais) | |||
Droits : © Inria Bordeaux - Sud-Ouest Auteur(s) : THORPE Simon 10-07-2015 Description : 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. Mots-clés libres : neurosciences,information visuelle,extraction valeur des images | TECHNIQUE Type : image en mouvement Format : video/x-flv Source(s) : rtmpt://fms2.cerimes.fr:80/vod/fuscia/reconnaissance.d.objets.une.problematique.resolue.has.object.vision.been.solved._23890/interfaces_simon.thorpe._compresse.e.mov | ||
Entrepôt d'origine : Canal-u.fr Identifiant : oai:canal-u.fr:23890 Type de ressource : Ressource documentaire | |||
| Exporter au format XML |
Ressource pédagogique
| Reconnaissance d’objets, une problématique résolue ? / Has object vision been solved? (en Anglais) | |||||||||
Identifiant de la fiche : 23890 Schéma de la métadonnée : LOMv1.0, LOMFRv1.0 Droits : libre de droits, gratuit Droits réservés à l'éditeur et aux auteurs. © Inria Bordeaux - Sud-Ouest Auteur(s) : THORPE SIMON Éditeur(s) : INRIA (Institut national de recherche en informatique et automatique) 10-07-2015 Description : 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. Mots-clés libres : neurosciences, information visuelle, extraction valeur des images
| PEDAGOGIQUE Type pédagogique : cours / présentation Niveau : doctorat TECHNIQUE Type de contenu : image en mouvement Format : video/x-flv Taille : 720.69 Mo Durée d'exécution : 1 heure 25 minutes 45 secondes RELATIONS Cette ressource fait partie de : | ||||||||
Entrepôt d'origine : Canal-u.fr Identifiant : oai:canal-u.fr:23890 Type de ressource : Ressource pédagogique | |||||||||
| Exporter au format XML |