Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
A hybrid learning network for shift-invariant recognition
Autore:
Wang, RY;
Indirizzi:
Harvey Mudd Coll, Dept Engn, Claremont, CA 91711 USA Harvey Mudd Coll Claremont CA USA 91711 ept Engn, Claremont, CA 91711 USA
Titolo Testata:
NEURAL NETWORKS
fascicolo: 8, volume: 14, anno: 2001,
pagine: 1061 - 1073
SICI:
0893-6080(200110)14:8<1061:AHLNFS>2.0.ZU;2-P
Fonte:
ISI
Lingua:
ENG
Soggetto:
ORDER NEURAL NETWORKS; PATTERN-RECOGNITION; STRIATE CORTEX; ORIENTATION; POSITION; ROTATION; MONKEY;
Keywords:
neural networks; shape recognition; invariant recognition;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
Citazioni:
29
Recensione:
Indirizzi per estratti:
Indirizzo: Wang, RY Harvey Mudd Coll, Dept Engn, Claremont, CA 91711 USA Harvey Mudd Coll Claremont CA USA 91711 Claremont, CA 91711 USA
Citazione:
R.Y. Wang, "A hybrid learning network for shift-invariant recognition", NEURAL NETW, 14(8), 2001, pp. 1061-1073

Abstract

A neural network and the associated learning algorithm are presented as a generic approach for invariant recognition of visual patterns independent of their geometric attributes, such as spatial location, orientation and scale. The network is a multi-layer hierarchy with each layer composed of a set of groups of nodes. The groups of the input layer represent local areas spatially arranged in the visual field according to the geometric variations. Each node in the subsequent higher layers receives input laterally from other groups of the same layer as well as vertically from the layer below. The learning that takes place in the vertical feed forward paths between layers is based on an unsupervised hybrid algorithm combining both competitivelearning and Hebbian learning. As the result of the architecture and the hybrid learning, the desired invariant recognition emerges at the output layer of the network. The network can serve as a simple and biologically plausible computational model to account for the invariant object recognition inthe biological visual system. Also, as the algorithm is generic and robust, it can be applied to solve various practical recognition problems. (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 22/01/20 alle ore 06:25:21