Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Face identification using one spike per neuron: resistance to image degradations
Autore:
Delorme, A; Thorpe, SJ;
Indirizzi:
Ctr Rech Cerveau & Cognit UMR 5549, F-31062 Toulouse, France Ctr Rech Cerveau & Cognit UMR 5549 Toulouse France F-31062 louse, France
Titolo Testata:
NEURAL NETWORKS
fascicolo: 6-7, volume: 14, anno: 2001,
pagine: 795 - 803
SICI:
0893-6080(200107/09)14:6-7<795:FIUOSP>2.0.ZU;2-F
Fonte:
ISI
Lingua:
ENG
Soggetto:
CAT VISUAL-CORTEX; SYNAPTIC EFFICACY; INFORMATION; PRIMATE; CELL; DISCRIMINATION; INHIBITION; MONKEYS; BURSTS; COLOR;
Keywords:
computation using spikes; feedforward propagation; visual system; face recognition; rank order coding; noise; contrast variations; image processing;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
Citazioni:
42
Recensione:
Indirizzi per estratti:
Indirizzo: Delorme, A Ctr Rech Cerveau & Cognit UMR 5549, 133 Route Narbonne, F-31062Toulouse, France Ctr Rech Cerveau & Cognit UMR 5549 133 Route Narbonne Toulouse France F-31062
Citazione:
A. Delorme e S.J. Thorpe, "Face identification using one spike per neuron: resistance to image degradations", NEURAL NETW, 14(6-7), 2001, pp. 795-803

Abstract

The short response latencies of face selective neurons in the inferotemporal cortex impose major constraints on models of visual processing. It appears that visual information must essentially propagate in a feed-forward fashion with most neurons only having time to fire one spike. We hypothesize that flashed stimuli can be encoded by the order of firing of ganglion cellsin the retina and propose a neuronal mechanism, that could be related to fast shunting inhibition, to decode such information. Based on these assumptions, we built a three-layered neural network of retino-topically organizedneuronal maps. We showed, by using, a learning rule involving spike timingdependant plasticity, that neuronal maps in the output layer can be trained to recognize natural photographs of faces. Not only was the model able togeneralize to novel views of the same faces, it was also remarkably resistant to image noise and reductions in contrast. (C) 2001 Elsevier Science Ltd. All rights reserved.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 28/01/20 alle ore 14:46:42