Multilayer Network Learning Algorithm Based on Pattern Search Method

Xu-Gang WANG  Zheng TANG  Hiroki TAMURA  Masahiro ISHII  

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E86-A   No.7   pp.1869-1875
Publication Date: 2003/07/01
Online ISSN: 
Print ISSN: 0916-8508
Type of Manuscript: PAPER
Category: Neural Networks and Bioengineering
multilayer neural networks,  pattern search method,  backpropagation,  learning,  

Full Text: PDF>>
Buy this Article

A new multilayer artificial neural network learning algorithm based on the pattern search method is proposed. The learning algorithm is designed to provide a very simple and effective means of searching the minima of an objective function directly without any knowledge of its derivatives. We test this algorithm on benchmark problems, such as exclusive-or (XOR), parity and alphabetic character learning problems. For all problems, the systems are shown to be trained efficiently by our algorithm. As a simple direct search algorithm, it can be applied to hardware implementations easily.