HOPFIELD NEURAL-NETWORK LEARNING USING DIRECT GRADIENT DESCENT OF ENERGY FUNCTION

Authors
TANG Z TASHIMA K HEBISHIMA H ISHIZUKA O TANNO K
Citation
Z. Tang et al., HOPFIELD NEURAL-NETWORK LEARNING USING DIRECT GRADIENT DESCENT OF ENERGY FUNCTION, IEICE transactions on fundamentals of electronics, communications and computer science, E79A(2), 1996, pp. 258-261
Citations number
10
Categorie Soggetti
Engineering, Eletrical & Electronic","Computer Science Hardware & Architecture","Computer Science Information Systems
Journal title
IEICE transactions on fundamentals of electronics, communications and computer science → ACNP
ISSN journal
09168508
Volume
E79A
Issue
2
Year of publication
1996
Pages
258 - 261
Database
ISI
SICI code
0916-8508(1996)E79A:2<258:HNLUDG>2.0.ZU;2-0
Abstract
A direct gradient descent learning algorithm of energy function in Hop field neural networks is proposed. The gradient descent learning is no t performed on usual error functions, but the Hopfield energy function s directly. We demonstrate the algorithm by testing it on an analog-to -digital conversion and an associative memory problems.