A single-iteration threshold Hamming network.
IEEE Trans Neural Netw
; 6(1): 261-6, 1995.
Article
em En
| MEDLINE
| ID: mdl-18263307
ABSTRACT
We analyze in detail the performance of a Hamming network classifying inputs that are distorted versions of one of its m stored memory patterns, each being a binary vector of length n. It is shown that the activation function of the memory neurons in the original Hamming network may be replaced by a simple threshold function. By judiciously determining the threshold value, the "winner-take-all" subnet of the Hamming network (known to be the essential factor determining the time complexity of the network's computation) may be altogether discarded. For m growing exponentially in n, the resulting threshold Hamming network correctly classifies the input pattern in a single iteration, with probability approaching 1.
Buscar no Google
Base de dados:
MEDLINE
Idioma:
En
Ano de publicação:
1995
Tipo de documento:
Article