DYNAMICS OF FULLY COMPLEX-VALUED NEURAL NETWORKS

被引：123

作者：

HIROSE, A

机构：

[1] Research Center for Advanced Science and Technology (RCAST), University of Tokyo, Meguro-ku, Tokyo 153

来源：

ELECTRONICS LETTERS | 1992年 / 28卷 / 16期

关键词：

NEURAL NETWORKS;

D O I：

10.1049/el:19920948

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

A novel neural network that processes input vectors and attractors fully in complex space using complex weights is proposed. Real and imaginary data are treated consistently with an equivalent significance in nondegenerate complex space. This network can be applied for ill-posed problems concerning realistic physical fields and continuous motion controls. The dynamics are presented and demonstrated.

引用

页码：1492 / 1494

页数：3

共 7 条

[1] STATISTICAL NEURODYNAMICS OF ASSOCIATIVE MEMORY [J].

AMARI, S ;

MAGINU, K .

NEURAL NETWORKS, 1988, 1 (01) :63-73

[2] STABILITY AND ATTRACTIVITY IN ASSOCIATIVE MEMORY NETWORKS [J].

COTTRELL, M .

BIOLOGICAL CYBERNETICS, 1988, 58 (02) :129-139

[3] NEURAL NETWORKS AND PHYSICAL SYSTEMS WITH EMERGENT COLLECTIVE COMPUTATIONAL ABILITIES [J].

HOPFIELD, JJ .

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA-BIOLOGICAL SCIENCES, 1982, 79 (08) :2554-2558

[4]

Kohonen T., 1988, SELF ORG ASS MEMORY

[5]

KONO T, 1990, IEICE TECH REP, P7

[6]

MORITA M, 1990, IEICE T D, V2, P232

[7]

TSURUOKA H, 1992, P ANN C JAPANESE NEU

← 1 →