A bidirectional heteroassociative memory for binary and grey-level patterns.
IEEE Trans Neural Netw
; 17(2): 385-96, 2006 Mar.
Article
en En
| MEDLINE
| ID: mdl-16566466
ABSTRACT
Typical bidirectional associative memories (BAM) use an offline, one-shot learning rule, have poor memory storage capacity, are sensitive to noise, and are subject to spurious steady states during recall. Recent work on BAM has improved network performance in relation to noisy recall and the number of spurious attractors, but at the cost of an increase in BAM complexity. In all cases, the networks can only recall bipolar stimuli and, thus, are of limited use for grey-level pattern recall. In this paper, we introduce a new bidirectional heteroassociative memory model that uses a simple self-convergent iterative learning rule and a new nonlinear output function. As a result, the model can learn online without being subject to overlearning. Our simulation results show that this new model causes fewer spurious attractors when compared to others popular BAM networks, for a comparable performance in terms of tolerance to noise and storage capacity. In addition, the novel output function enables it to learn and recall grey-level patterns in a bidirectional way.
Buscar en Google
Colección:
01-internacional
Banco de datos:
MEDLINE
Asunto principal:
Algoritmos
/
Análisis Numérico Asistido por Computador
/
Reconocimiento de Normas Patrones Automatizadas
/
Inteligencia Artificial
/
Interpretación de Imagen Asistida por Computador
/
Técnicas de Apoyo para la Decisión
/
Modelos Teóricos
Tipo de estudio:
Evaluation_studies
/
Prognostic_studies
Idioma:
En
Revista:
IEEE Trans Neural Netw
Asunto de la revista:
INFORMATICA MEDICA
Año:
2006
Tipo del documento:
Article
País de afiliación:
Canadá