Multilayer Network Learning Algorithm Based on Pattern Search Method

Xu-Gang WANG; Zheng TANG; Hiroki TAMURA; Masahiro ISHII

Multilayer Network Learning Algorithm Based on Pattern Search Method

Xu-Gang WANG, Zheng TANG, Hiroki TAMURA, Masahiro ISHII

Full Text Views

0

Share
Cite this

Summary :

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.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E86-A No.7 pp.1869-1875

Publication Date: 2003/07/01

Publicized

Online ISSN

DOI

Type of Manuscript: PAPER

Category: Neural Networks and Bioengineering

Cite this

Copy

Xu-Gang WANG, Zheng TANG, Hiroki TAMURA, Masahiro ISHII, "Multilayer Network Learning Algorithm Based on Pattern Search Method" in IEICE TRANSACTIONS on Fundamentals, vol. E86-A, no. 7, pp. 1869-1875, July 2003, doi: .
Abstract: 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.
URL: https://globals.ieice.org/en_transactions/fundamentals/10.1587/e86-a_7_1869/_p

Copy

@ARTICLE{e86-a_7_1869,
author={Xu-Gang WANG, Zheng TANG, Hiroki TAMURA, Masahiro ISHII, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Multilayer Network Learning Algorithm Based on Pattern Search Method},
year={2003},
volume={E86-A},
number={7},
pages={1869-1875},
abstract={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.},
keywords={},
doi={},
ISSN={},
month={July},}

Copy

TY - JOUR
TI - Multilayer Network Learning Algorithm Based on Pattern Search Method
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1869
EP - 1875
AU - Xu-Gang WANG
AU - Zheng TANG
AU - Hiroki TAMURA
AU - Masahiro ISHII
PY - 2003
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E86-A
IS - 7
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - July 2003
AB - 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.
ER -