Transactions of the Institute of Systems, Control and Information Engineers
Online ISSN : 2185-811X
Print ISSN : 1342-5668
ISSN-L : 1342-5668
A New Error Back Propagation Method for a Multilayer Neural Network and Its Algebraic Properties
Yoshihiro YAMAMOTO
Author information

1996 Volume 9 Issue 5 Pages 201-209


The back propagation method is well known as a supervised learning rule of a neural network.
In this paper, a new learning rule is proposed where the output error vector is adjusted to zero by correcting two kinds of vectors, the one is weighting vectors (matrix) and the other is an input vector of the layer. The corrected input vector has a role of a tentative teacher of the following layer. In this way, the output error is propagated backward, and is partly corrected by each weighting vector.
Computatinal method is also presented for a matrix inversion which is required in the proposed method and nonsingularity of the matix is discussed.
Simulation result of the Exclusive-OR problem shows the effectiveness of the proposed method.

Information related to the author
© The Institute of Systems, Control and Information Engineers
Next article