Learning of a Multi-Valued Neural Network and Its Application

Ryuzo TAKIYAMA  Koichiro KUBO  

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E76-A   No.6   pp.873-877
Publication Date: 1993/06/25
Online ISSN: 
Print ISSN: 0916-8508
Type of Manuscript: Special Section PAPER (Special Section on Papers Selected from 1992 Joint Technical Conference on Circuits/Systems,Computers and Communications (JTC-CSCC'92))
Category: Nonlinear Circuits and Neural Nets
neural networks,  optimization,  

Full Text: PDF>>
Buy this Article

A learning procedure of a three layer neural network with limited structure, called a multi-valued neural network, is proposed. The three layer net has a single linear neuron in its output layer. All input weights of a number of hidden neurons are identical. The network takes k+1 distinct stable values, where k is the number of hidden neurons. The proposed learning procedure consists of two parts, Phase and Phase . The former is one for the learning of weights between the hidden and output layers, and the latter is one for those between the input and the hidden layers. The network is applied to classification of numerals, which shows the effectiveness of the proposed learning procedure.