Determining initial weights of feedforward neural networks based on least squares method

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journal

18 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)13-17
Journal / PublicationNeural Processing Letters
Volume2
Issue number2
Publication statusPublished - Mar 1995

Abstract

An algorithm for determining the optimal initial weights of feedforward neural networks based on linear algebraic methods is presented. With the optimal initial weights, the initial network error is enormous smaller. In one of the examples presented in this letter, the achieved accuracy is sufficient for direct application. If further smaller network error is required, the networks can be trained using backpropagation algorithm. © 1995 Kluwer Academic Publishers.