LEARNING AND GENERALIZATION CHARACTERISTICS OF THE RANDOM VECTOR FUNCTIONAL-LINK NET

被引：838

作者：

PAO, YH ^{[1
]}

PARK, GH ^{[1
]}

SOBAJIC, DJ ^{[1
]}

机构：

[1] CASE WESTERN RESERVE UNIV,CLEVELAND,OH 44106

来源：

NEUROCOMPUTING | 1994年 / 6卷 / 02期

关键词：

NEURAL NET; FUNCTIONAL-LINK NET; FUNCTIONAL MAPPING; GENERALIZED DELTA RULE; AUTO-ENHANCEMENT; OVERTRAINING AND GENERALIZATION;

D O I：

10.1016/0925-2312(94)90053-1

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper we explore and discuss the learning and generalization characteristics of the random vector version of the Functional-link net and compare these with those attainable with the GDR algorithm. This is done for a well-behaved deterministic function and for real-world data. It seems that 'overtraining' occurs for stochastic mappings. Otherwise there is saturation of training.

引用

页码：163 / 180

页数：18

共 16 条

[1]

[Anonymous], 1987, LEARNING INTERNAL RE

[2] APPROXIMATION OF A FUNCTION AND ITS DERIVATIVE WITH A NEURAL NETWORK [J].