Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
A competitive-layer model for feature binding and sensory segmentation
Autore:
Wersing, H; Steil, JJ; Ritter, H;
Indirizzi:
HONDA R&D Europe Germany, D-63073 Offenbach Main, Germany HONDA R&D EuropeGermany Offenbach Main Germany D-63073 ch Main, Germany Univ Bielefeld, Fac Technol, D-33501 Bielefeld, Germany Univ Bielefeld Bielefeld Germany D-33501 nol, D-33501 Bielefeld, Germany
Titolo Testata:
NEURAL COMPUTATION
fascicolo: 2, volume: 13, anno: 2001,
pagine: 357 - 387
SICI:
0899-7667(200102)13:2<357:ACMFFB>2.0.ZU;2-7
Fonte:
ISI
Lingua:
ENG
Soggetto:
PRIMARY VISUAL-CORTEX; MACAQUE MONKEY; STRIATE CORTEX; NEURAL OSCILLATORS; IMAGE SEGMENTATION; NETWORKS; NEURONS; OPTIMIZATION; INTEGRATION; CONNECTIONS;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Life Sciences
Engineering, Computing & Technology
Citazioni:
62
Recensione:
Indirizzi per estratti:
Indirizzo: Wersing, H HONDA R&D Europe Germany, Carl Legien Str 30, D-63073 OffenbachMain, Germany HONDA R&D Europe Germany Carl Legien Str 30 Offenbach Main Germany D-63073
Citazione:
H. Wersing et al., "A competitive-layer model for feature binding and sensory segmentation", NEURAL COMP, 13(2), 2001, pp. 357-387

Abstract

We present a recurrent neural network for feature binding and sensory segmentation: the competitive-layer model (CLM). The CLM uses topographically structured competitive and cooperative interactions in a layered network to partition a set of input features into salient groups. The dynamics is formulated within a standard additive recurrent network with linear threshold neurons. Contextual relations among features are coded by pairwise compatibilities, which define an energy function to be minimized by the neural dynamics. Due to the usage of dynamical winner-take-all circuits, the model gains more flexible response properties than spin models of segmentation by exploiting amplitude information in the grouping process. We prove analytic results on the convergence and stable attractors of the CLM, which generalizeearlier results on winner-take-all networks, and incorporate deterministicannealing for robustness against local minima. The piecewise linear dynamics of the CLM allows a linear eigensubspace analysis, which we use to analyze the dynamics of binding in conjunction with annealing. For the example of contour detection, we show how the CLM can integrate figure-ground segmentation and grouping into a unified model.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 25/01/20 alle ore 03:22:01