ON THE SEARCH FOR NEW LEARNING RULES FOR ANNS

被引：22

作者：

BENGIO, S

BENGIO, Y

CLOUTIER, J

机构：

[1] FRANCE TELECOM,CNET,TNT,RIO,LAB,F-22307 LANNION,FRANCE

[2] UNIV MONTREAL,DEPT IRO,MONTREAL,PQ H3C 3J7,CANADA

来源：

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

关键词：

D O I：

10.1007/BF02279935

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 present a framework where a learning rule can be optimized within a parametric learning rule space. We define what we call parametric learning rules and present a theoretical study of their generalization properties when estimated from a set of learning tasks and tested over another set of tasks. We corroborate the results of this study with practical experiments.

引用

页码：26 / 30

页数：5