THE SOFTENING LEARNING PROCEDURE

被引：6

作者：

TSAIH, RR

机构：

[1] Department of Management Information Systems National Chengchi University, Taipei

来源：

MATHEMATICAL AND COMPUTER MODELLING | 1993年 / 18卷 / 08期

关键词：

LAYERED FEEDFORWARD NETWORKS; LINEARLY SEPARATING CONDITION;

D O I：

10.1016/0895-7177(93)90163-S

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

Here, I present a learning algorithm, referred to as the softening learning algorithm, that imitates the way of learning in human beings. When we encounter a new case (a new input/output relationship), we first check if the knowledge we obtained so far could interpret it. If so, there is no further learning effort involved. If not, we might cram this unfamiliar case; then, meditate to reason out a way of integrating it into our knowledge.

引用

页码：61 / 64

页数：4