AN ONLINE LEARNING ALGORITHM FOR THE ORTHOGONAL WEIGHT ESTIMATION OF MLP

被引：1

作者：

PICAN, N

FORT, JC

ALEXANDRE, F

机构：

[1] INRIA LORRAINE,CRIN,CNRS,F-54602 VILLERS LES NANCY,FRANCE

[2] UNIV NANCY 1,DEPT MATH,F-54506 VANDOEUVRE NANCY,FRANCE

来源：

NEURAL PROCESSING LETTERS | 1994年 / 1卷 / 01期

关键词：

D O I：

10.1007/BF02312397

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We propose an on-line learning algorithm for Multi Layered Perceptrons (MLP) with an Orthogonal Weight Estimator (OWE) architecture. Such an architecture allows to dynamically and efficiently estimate the weights of a MLP in context dependent behaviour problems. The proposed learning algorithm attempts to solve the problem of time-consuming in the learning phase encountered to train these weight estimators.

引用

页码：21 / 24

页数：4