EVOLVING NEURAL NETWORKS WITH ITERATIVE LEARNING SCHEME FOR ASSOCIATIVE MEMORY

被引：12

作者：

FUJITA, S

NISHIMURA, H

机构：

[1] KOBE UNIV,GRAD SCH SCI & TECHNOL,KOBE 657,JAPAN

[2] HYOGO UNIV EDUC,DEPT INFORMAT SCI,YASHIRO,HYOGO 67314,JAPAN

来源：

NEURAL PROCESSING LETTERS | 1995年 / 2卷 / 04期

关键词：

D O I：

10.1007/BF02279930

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A locally iterative learning (LIL) rule is adapted to a model of the associative memory based on the evolving recurrent-type neural networks composed of growing neurons. There exist extremely different scale parameters of time, the individual learning time and the generation in evolution. This model allows us definite investigation on the interaction between learning and evolution. And the reinforcement of the robustness against the noise is also achieved in the evolutional scheme.

引用

页码：1 / 5

页数：5

共 10 条

[1]

Baldwin JM., 1896, AM NAT, V30, P441, DOI [10.1086/276408, DOI 10.1086/276408]

[2]

BRANKE J, 1995, 1ST P NORD WORKSH GE

[3] LEARNING OF CORRELATED PATTERNS IN SPIN-GLASS NETWORKS BY LOCAL LEARNING RULES [J].