MODIFIED HOPFIELD NEURAL NETWORKS FOR RETRIEVING THE OPTIMAL SOLUTION

被引：42

作者：

LEE, BW

SHEU, BJ

机构：

[1] UNIV SO CALIF,CTR NEURAL ENGN,LOS ANGELES,CA 90089

[2] UNIV SO CALIF,DEPT ELECT ENGN,INST SIGNAL & IMAGE PROC,LOS ANGELES,CA 90089

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 1991年 / 2卷 / 01期

关键词：

D O I：

10.1109/72.80300

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Due to the rugged energy function of the original Hopfield networks, the output is usually one local minimum in the energy function. This paper presents an analysis on the locations of local minima in Hopfield networks and describes a modified network architecture to eliminate such local minima. In particular, another amplifier is introduced at the processor nodes to give correction terms. This modified Hopfield network has been successfully applied to the construction of analog-to-digital converters with optimal solutions. Experimental results on the voltage transfer characteristics of data converters are presented.

引用

页码：137 / 142

页数：6

共 15 条

[11]

LEE BW, 1990, JUN IEEE INT JOINT C, V2, P575

[12] THE CAPACITY OF THE HOPFIELD ASSOCIATIVE MEMORY [J].

MCELIECE, RJ ;

POSNER, EC ;

RODEMICH, ER ;

VENKATESH, SS .

IEEE TRANSACTIONS ON INFORMATION THEORY, 1987, 33 (04) :461-482

[13]

MOOPENN A, 1987, MAR IEEE T SYST MAN, V17, P326

[14] SIMPLE NEURAL OPTIMIZATION NETWORKS - AN A/D CONVERTER, SIGNAL DECISION CIRCUIT, AND A LINEAR-PROGRAMMING CIRCUIT [J].

TANK, DW ;

HOPFIELD, JJ .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1986, 33 (05) :533-541

[15] IMAGE-RESTORATION USING A NEURAL NETWORK [J].

ZHOU, YT ;

CHELLAPPA, R ;

VAID, A ;

JENKINS, BK .

IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1988, 36 (07) :1141-1151

← 1 2 →