Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Sequence processing neural network with a non-monotonic transfer function
Autore:
Katayama, K; Horiguchi, T;
Indirizzi:
Tohoku Univ, Grad Sch Informat Sci, Dept Math & Comp Sci, Sendai, Miyagi 9808579, Japan Tohoku Univ Sendai Miyagi Japan 9808579 ci, Sendai, Miyagi 9808579, Japan
Titolo Testata:
JOURNAL OF THE PHYSICAL SOCIETY OF JAPAN
fascicolo: 5, volume: 70, anno: 2001,
pagine: 1300 - 1314
SICI:
0031-9015(200105)70:5<1300:SPNNWA>2.0.ZU;2-R
Fonte:
ISI
Lingua:
ENG
Soggetto:
ASSOCIATIVE MEMORY; STORAGE CAPACITY; SPIN-GLASS; PARALLEL DYNAMICS; MODEL; SATURATION; SYSTEMS;
Keywords:
neural network; sequence processing; non-monotonic transfer function; Hebb rule; generating-function method; numerical simulation;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Physical, Chemical & Earth Sciences
Citazioni:
31
Recensione:
Indirizzi per estratti:
Indirizzo: Katayama, K Tohoku Univ, Grad Sch Informat Sci, Dept Math & Comp Sci, Sendai, Miyagi 9808579, Japan Tohoku Univ Sendai Miyagi Japan 9808579 Miyagi 9808579, Japan
Citazione:
K. Katayama e T. Horiguchi, "Sequence processing neural network with a non-monotonic transfer function", J PHYS JPN, 70(5), 2001, pp. 1300-1314

Abstract

We investigate storage capacity and retrieval property for a synchronous fully connected neural network with a non-monotonic transfer function which retrieves sequences of patterns, by an analytic method and also by numerical simulations. Because of asymmetry of interactions and non-monotonicity ofthe transfer function, it is difficult to use conventional methods of the equilibrium statistical mechanics in order to investigate the network. We then use a generating function method of path-integral representation, and obtain equations for dynamical order parameters in the stationary state. We clarify that the network with the non-monotonic transfer function retrievesmore sequences of patterns than that with a monotonic transfer function atzero temperature when non-monotonicity of the transfer function is selected optimally. It is also clarified that some chaotic behavior appears in solutions for the equations of the dynamical order parameters when non-monotonicity of the transfer function increases. The analytic results are in excellent agreement with the results obtained by numerical simulations.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 12/07/20 alle ore 06:11:42