A new supervised learning algorithm for multilayered and interconnected neural networks

Author

Yamamoto, Yoshihiro ; Nikiforuk, Peter N.

Author_Institution

Dept. of Inf. & Knowledge Eng., Tottori Univ., Japan

Volume

11

Issue

1

fYear

2000

fDate

1/1/2000 12:00:00 AM

Firstpage

36

Lastpage

46

Abstract

A learning algorithm is presented for supervised learning of multilayered and interconnected neural networks without using a gradient method. First, fictitious teacher signals for the outputs of each hidden unit are algebraically determined by an error backpropagation (EBP) method. Then, the weight parameters are determined by using an exponentially weighted least squares (EWLS) method. This is called the EBP-EWLS algorithm for a multilayered neural network. For an interconnected neural network, the mathematical description of the neural network is arranged in the form for which the EBP-EWLS algorithm can be applied. Simulation studies have verified the proposed technique

Keywords

backpropagation; least squares approximations; multilayer perceptrons; error backpropagation method; exponentially weighted least squares method; fictitious teacher signals; hidden units; interconnected neural networks; supervised learning algorithm; Backpropagation algorithms; Control systems; Feedforward neural networks; Gradient methods; Knowledge engineering; Least squares methods; Multi-layer neural network; Neural networks; Pattern recognition; Supervised learning;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.822508

Filename

822508