A Genetic Algorithm Based Variable Structure Neural Network

S. H. Ling; H. K. Lam; Hung Fat Frank Leung; Y. S. Lee

doi:10.1109/IECON.2003.1280020

A Genetic Algorithm Based Variable Structure Neural Network

S. H. Ling, H. K. Lam, Hung Fat Frank Leung, Y. S. Lee

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

7 Citations (Scopus)

Abstract

This paper presents a neural network model with a variable structure, which is trained by genetic algorithm (GA). The proposed neural network consists of a Neural Network with a Node-to-Node Relationship (N4R) and a Network Switch Controller (NSC). In the N4R, a modified neuron model with two activation functions in the hidden layer, and switches in its links are introduced. The NSC controls the switches in the N4R. The proposed neural network can model different input patterns with variable network structures. The proposed neural network provides better result and learning ability than traditional feed forward neural networks. Two application examples on XOR problem and hand-written pattern recognition are given to illustrate the merits of the proposed network.

Original language	English
Title of host publication	IECON Proceedings (Industrial Electronics Conference)
Pages	436-441
Number of pages	6
DOIs	https://doi.org/10.1109/IECON.2003.1280020
Publication status	Published - 1 Dec 2003
Event	The 29th Annual Conference of the IEEE Industrial Electronics Society - Roanoke, VA, United States Duration: 2 Nov 2003 → 6 Nov 2003

Conference

Conference	The 29th Annual Conference of the IEEE Industrial Electronics Society
Country/Territory	United States
City	Roanoke, VA
Period	2/11/03 → 6/11/03

Keywords

Genetic algorithm
Hand-written pattern recognition
Neural network

ASJC Scopus subject areas

Electrical and Electronic Engineering

More information

10.1109/IECON.2003.1280020

http://hdl.handle.net/10397/1352

Cite this

@inproceedings{e02f5e69850143d3823441d79260c7d7,

title = "A Genetic Algorithm Based Variable Structure Neural Network",

abstract = "This paper presents a neural network model with a variable structure, which is trained by genetic algorithm (GA). The proposed neural network consists of a Neural Network with a Node-to-Node Relationship (N4R) and a Network Switch Controller (NSC). In the N4R, a modified neuron model with two activation functions in the hidden layer, and switches in its links are introduced. The NSC controls the switches in the N4R. The proposed neural network can model different input patterns with variable network structures. The proposed neural network provides better result and learning ability than traditional feed forward neural networks. Two application examples on XOR problem and hand-written pattern recognition are given to illustrate the merits of the proposed network.",

keywords = "Genetic algorithm, Hand-written pattern recognition, Neural network",

author = "Ling, {S. H.} and Lam, {H. K.} and Leung, {Hung Fat Frank} and Lee, {Y. S.}",

year = "2003",

month = dec,

day = "1",

doi = "10.1109/IECON.2003.1280020",

language = "English",

pages = "436--441",

booktitle = "IECON Proceedings (Industrial Electronics Conference)",

note = "The 29th Annual Conference of the IEEE Industrial Electronics Society ; Conference date: 02-11-2003 Through 06-11-2003",

}

TY - GEN

T1 - A Genetic Algorithm Based Variable Structure Neural Network

AU - Ling, S. H.

AU - Lam, H. K.

AU - Leung, Hung Fat Frank

AU - Lee, Y. S.

PY - 2003/12/1

Y1 - 2003/12/1

N2 - This paper presents a neural network model with a variable structure, which is trained by genetic algorithm (GA). The proposed neural network consists of a Neural Network with a Node-to-Node Relationship (N4R) and a Network Switch Controller (NSC). In the N4R, a modified neuron model with two activation functions in the hidden layer, and switches in its links are introduced. The NSC controls the switches in the N4R. The proposed neural network can model different input patterns with variable network structures. The proposed neural network provides better result and learning ability than traditional feed forward neural networks. Two application examples on XOR problem and hand-written pattern recognition are given to illustrate the merits of the proposed network.

AB - This paper presents a neural network model with a variable structure, which is trained by genetic algorithm (GA). The proposed neural network consists of a Neural Network with a Node-to-Node Relationship (N4R) and a Network Switch Controller (NSC). In the N4R, a modified neuron model with two activation functions in the hidden layer, and switches in its links are introduced. The NSC controls the switches in the N4R. The proposed neural network can model different input patterns with variable network structures. The proposed neural network provides better result and learning ability than traditional feed forward neural networks. Two application examples on XOR problem and hand-written pattern recognition are given to illustrate the merits of the proposed network.

KW - Genetic algorithm

KW - Hand-written pattern recognition

KW - Neural network

UR - http://www.scopus.com/inward/record.url?scp=1442304902&partnerID=8YFLogxK

U2 - 10.1109/IECON.2003.1280020

DO - 10.1109/IECON.2003.1280020

M3 - Conference article published in proceeding or book

SP - 436

EP - 441

BT - IECON Proceedings (Industrial Electronics Conference)

T2 - The 29th Annual Conference of the IEEE Industrial Electronics Society

Y2 - 2 November 2003 through 6 November 2003

ER -

A Genetic Algorithm Based Variable Structure Neural Network

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this