For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Error-Correction Learning of Three Layer Neural Networks Based on Linear-Homogeneous Expressions
Ryuzo TAKIYAMA Kimitoshi FUKUDOME
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 1993/04/25
Print ISSN: 0916-8508
Type of Manuscript: PAPER
Category: Neural Networks
neural networks, optimization,
Full Text: PDF>>
The three layer neural network (TLNN) is treated, where the nonlinearity of a neuron is of signum. First we propose an expression of the discriminant function of the TLNN, which is called a linear-homogeneous expression. This expression allows the differentiation in spite of the signum property of the neuron. Subsequently a learning algorithm is proposed based on the linear-homogeneous form. The algorithm is an error-correction procedure, which gives a mathematical foundation to heuristic error-correction learnings described in various literatures.