Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Layered neural network with intra-layer connections using Q-states clock neurons
Autore:
Katayama, K; Horiguchi, T;
Indirizzi:
Tohoku Univ, GSIS, Dept Comp & Math Sci, Sendai, Miyagi 9808579, Japan Tohoku Univ Sendai Miyagi Japan 9808579 ci, Sendai, Miyagi 9808579, Japan
Titolo Testata:
PHYSICA A
fascicolo: 3-4, volume: 297, anno: 2001,
pagine: 532 - 548
SICI:
0378-4371(20010815)297:3-4<532:LNNWIC>2.0.ZU;2-3
Fonte:
ISI
Lingua:
ENG
Soggetto:
RANDOM SYNAPTIC DILUTION; SPIN-GLASS; STATISTICAL-MECHANICS; NATURAL FREQUENCIES; ASSOCIATIVE MEMORY; DYNAMICS; MODEL; PATTERNS; SATURATION; CORTEX;
Keywords:
neural network; Hebb rule; Q-states clock neuron; oscillatory neuron; storage capacity; replica method;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Physical, Chemical & Earth Sciences
Citazioni:
29
Recensione:
Indirizzi per estratti:
Indirizzo: Horiguchi, T Tohoku Univ, GSIS, Dept Comp & Math Sci, Sendai, Miyagi 9808579, Japan Tohoku Univ Sendai Miyagi Japan 9808579 iyagi 9808579, Japan
Citazione:
K. Katayama e T. Horiguchi, "Layered neural network with intra-layer connections using Q-states clock neurons", PHYSICA A, 297(3-4), 2001, pp. 532-548

Abstract

We investigate storage capacity of a fully connected layered neural network with Q(greater than or equal to 2)-states clock neurons, including Q = infinity (corresponding to oscillatory neurons) and with intra-layer connections, where random Q-values patterns are embedded into the network by the Hebbian learning rule. We assume that both of inter-layered neurons and intra-layered neurons are updated simultaneously. We are able to treat a recurrent network, a feed-forward network and a layered network with the intra-layer connections within the same framework by adjusting a parameter. We analyze an energy function of the network by using the replica method. We clarify that the storage capacity of the layered network with the intra-laver connections is enhanced in comparison with that of the recurrent network and that of the feed-forward network for Q = 2,3,4 and 5 at zero temperature; this is due to the competition between the inter-layer connections and the intra-layer connections. For Q greater than or equal to 6, including Q = infinity, the storage capacity at zero temperature is maximum for the feed-forward network. We obtain phase diagrams in a load-parameter versus temperature plane for the layered network with the intra-layer connections. (C) 2001 Elsevier Science B.V. All rights reserved.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 15/07/20 alle ore 14:46:43