A variable-parameter neural network trained by improved genetic algorithm and its application

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

doi:10.1109/IJCNN.2005.1556069

A variable-parameter neural network trained by improved genetic algorithm and its application

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

The Hong Kong Polytechnic University

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

4 Citations (Scopus)

Abstract

This paper presents a neural network with variable parameters. These variable parameters adapt to the changes of the input environment, and tackle different input data sets in a large domain. Each input data set is effectively handled by its corresponding set of network parameters. Thus, the proposed neural network exhibits a better learning and generalization ability than a traditional one. An improved genetic algorithm [1] is proposed to train the network parameters. An application example on hand-written pattern recognition will be presented to verify and illustrate the improvement.

Original language	English
Title of host publication	Proceedings of the International Joint Conference on Neural Networks
Pages	1343-1348
Number of pages	6
DOIs	https://doi.org/10.1109/IJCNN.2005.1556069
Publication status	Published - 1 Dec 2005
Event	International Joint Conference on Neural Networks, IJCNN 2005 - Montreal, QC, Canada Duration: 31 Jul 2005 → 4 Aug 2005

Conference

Conference	International Joint Conference on Neural Networks, IJCNN 2005
Country/Territory	Canada
City	Montreal, QC
Period	31/07/05 → 4/08/05

ASJC Scopus subject areas

Software

More information

10.1109/IJCNN.2005.1556069

http://hdl.handle.net/10397/1396

Cite this

@inproceedings{d5092126e29c4497b4bd721adb1ec32e,

title = "A variable-parameter neural network trained by improved genetic algorithm and its application",

abstract = "This paper presents a neural network with variable parameters. These variable parameters adapt to the changes of the input environment, and tackle different input data sets in a large domain. Each input data set is effectively handled by its corresponding set of network parameters. Thus, the proposed neural network exhibits a better learning and generalization ability than a traditional one. An improved genetic algorithm [1] is proposed to train the network parameters. An application example on hand-written pattern recognition will be presented to verify and illustrate the improvement.",

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

year = "2005",

month = dec,

day = "1",

doi = "10.1109/IJCNN.2005.1556069",

language = "English",

pages = "1343--1348",

booktitle = "Proceedings of the International Joint Conference on Neural Networks",

note = "International Joint Conference on Neural Networks, IJCNN 2005 ; Conference date: 31-07-2005 Through 04-08-2005",

}

A variable-parameter neural network trained by improved genetic algorithm and its application. / Ling, S. H.; Lam, H. K.; Leung, Hung Fat Frank.
Proceedings of the International Joint Conference on Neural Networks. 2005. p. 1343-1348 1556069.

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

TY - GEN

T1 - A variable-parameter neural network trained by improved genetic algorithm and its application

AU - Ling, S. H.

AU - Lam, H. K.

AU - Leung, Hung Fat Frank

PY - 2005/12/1

Y1 - 2005/12/1

N2 - This paper presents a neural network with variable parameters. These variable parameters adapt to the changes of the input environment, and tackle different input data sets in a large domain. Each input data set is effectively handled by its corresponding set of network parameters. Thus, the proposed neural network exhibits a better learning and generalization ability than a traditional one. An improved genetic algorithm [1] is proposed to train the network parameters. An application example on hand-written pattern recognition will be presented to verify and illustrate the improvement.

AB - This paper presents a neural network with variable parameters. These variable parameters adapt to the changes of the input environment, and tackle different input data sets in a large domain. Each input data set is effectively handled by its corresponding set of network parameters. Thus, the proposed neural network exhibits a better learning and generalization ability than a traditional one. An improved genetic algorithm [1] is proposed to train the network parameters. An application example on hand-written pattern recognition will be presented to verify and illustrate the improvement.

UR - https://www.scopus.com/pages/publications/33750102262

U2 - 10.1109/IJCNN.2005.1556069

DO - 10.1109/IJCNN.2005.1556069

M3 - Conference article published in proceeding or book

SP - 1343

EP - 1348

BT - Proceedings of the International Joint Conference on Neural Networks

T2 - International Joint Conference on Neural Networks, IJCNN 2005

Y2 - 31 July 2005 through 4 August 2005

ER -

A variable-parameter neural network trained by improved genetic algorithm and its application

Abstract

Conference

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this