Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
A two-layer sparse coding model learns simple and complex cell receptive fields and topography from natural images
Autore:
Hyvarinen, A; Hoyer, PO;
Indirizzi:
Helsinki Univ Technol, Neural Networks Res Ctr, FIN-02015 Helsinki, Finland Helsinki Univ Technol Helsinki Finland FIN-02015 02015 Helsinki, Finland Univ Helsinki, Dept Psychol, Gen Psychol Div, FIN-00014 Helsinki, Finland Univ Helsinki Helsinki Finland FIN-00014 iv, FIN-00014 Helsinki, Finland
Titolo Testata:
VISION RESEARCH
fascicolo: 18, volume: 41, anno: 2001,
pagine: 2413 - 2423
SICI:
0042-6989(200108)41:18<2413:ATSCML>2.0.ZU;2-Y
Fonte:
ISI
Lingua:
ENG
Soggetto:
INDEPENDENT COMPONENT ANALYSIS; PRIMARY VISUAL-CORTEX; SPATIAL-FREQUENCY; STRIATE CORTEX; ORGANIZATION; ORIENTATION; FILTERS; NEURONS; MAPS; STATISTICS;
Keywords:
cortex; independent component analysis; natural images; neural networks; spatial vision;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Life Sciences
Citazioni:
49
Recensione:
Indirizzi per estratti:
Indirizzo: Hyvarinen, A Helsinki Univ Technol, Neural Networks Res Ctr, POB 5400, FIN-02015 Helsinki, Finland Helsinki Univ Technol POB 5400 Helsinki Finland FIN-02015 nd
Citazione:
A. Hyvarinen e P.O. Hoyer, "A two-layer sparse coding model learns simple and complex cell receptive fields and topography from natural images", VISION RES, 41(18), 2001, pp. 2413-2423

Abstract

The classical receptive fields of simple cells in the visual cortex have been shown to emerge from the statistical properties of natural images by forcing the cell responses to be maximally sparse, i.e. significantly activated only rarely. Here, we show that this single principle of sparseness can also lead to emergence of topography (columnar organization) and complex cell properties as well. These are obtained by maximizing the sparsenesses oflocally pooled energies, which correspond to complex cell outputs. Thus, we obtain a highly parsimonious model of how these properties of the visual cortex are adapted to the characteristics of the natural input. (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 01/04/20 alle ore 01:15:36