Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Mutual information of sparsely coded associative memory with self-control and ternary neurons
Autore:
Bolle, D; Dominguez, DRC; Amari, S;
Indirizzi:
Katholieke Univ Leuven, Inst Theoret Fys, B-3001 Louvain, Belgium Katholieke Univ Leuven Louvain Belgium B-3001 s, B-3001 Louvain, Belgium Univ Rey Juan Carlos, ESCET, Madrid 28933, Spain Univ Rey Juan Carlos Madrid Spain 28933 rlos, ESCET, Madrid 28933, Spain INTA, CAB Associate NASA Astrobiol, Madrid 28850, Spain INTA Madrid Spain 28850 AB Associate NASA Astrobiol, Madrid 28850, Spain RIKEN, Frontier Res Program, Wako, Saitama 35101, Japan RIKEN Wako Saitama Japan 35101 er Res Program, Wako, Saitama 35101, Japan
Titolo Testata:
NEURAL NETWORKS
fascicolo: 4-5, volume: 13, anno: 2000,
pagine: 455 - 462
SICI:
0893-6080(200005/06)13:4-5<455:MIOSCA>2.0.ZU;2-L
Fonte:
ISI
Lingua:
ENG
Soggetto:
ISING NEURAL NETWORKS; MULTISTATE NEURONS; RETRIEVAL; DYNAMICS; PATTERNS;
Keywords:
associative memory; ternary neurons; sparse coding; self-control dynamics; mutual information; storage capacity; basin of attraction;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
Citazioni:
29
Recensione:
Indirizzi per estratti:
Indirizzo: Bolle, D Katholieke Univ Leuven, Inst Theoret Fys, Celestijnenlaan 200 D, B-3001 Louvain, Belgium Katholieke Univ Leuven Celestijnenlaan 200 D Louvain Belgium B-3001
Citazione:
D. Bolle et al., "Mutual information of sparsely coded associative memory with self-control and ternary neurons", NEURAL NETW, 13(4-5), 2000, pp. 455-462

Abstract

The influence of a macroscopic time-dependent threshold on the retrieval dynamics of attractor associative memory models with ternary neurons {-1,0,+1} is examined. If the threshold is chosen appropriately as a function of the cross-talk noise and of the activity of the memorized patterns in the model, adapting itself in the course of the time evolution, it guarantees an autonomous functioning of the model. Especially in the limit of sparse coding, it is found that this self-control mechanism considerably improves the quality of the fixed-point retrieval dynamics, in particular the storage capacity, the basins of attraction and the information content. The mutual information is shown to be the relevant parameter to study the retrieval quality of such sparsely coded models. Numerical results confirm these observations. (C) 2000 Elsevier Science Ltd. All rights reserved.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 27/05/20 alle ore 12:38:40