A variable node-to-node-link neural network and its application to hand-written recognition

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

A variable node-to-node-link neural network and its application to hand-written recognition

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

The Hong Kong Polytechnic University

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

Abstract

This paper presents a variable node-to-node-link neural network (VN 2NN) trained by real-coded genetic algorithm (RCGA). The VN 2NN exhibits a node-to-node relationship in the hidden layer, and the network parameters are variable. These characteristics make the network adapt to the changes of the input environment, enable it to tackle different input sets distributed in a large domain. Each input data set is effectively handled by a corresponding set of network parameters. The set of parameters are governed by the other nodes. Taking the advantage of these features, the proposed network ensures better learning and generalization abilities. Application of the proposed network to hand-written graffiti recognition will be presented so as to illustrate the improvement.

Original language	English
Title of host publication	International Joint Conference on Neural Networks 2006, IJCNN '06
Pages	921-928
Number of pages	8
Publication status	Published - 1 Dec 2006
Event	International Joint Conference on Neural Networks 2006, IJCNN '06 - Vancouver, BC, Canada Duration: 16 Jul 2006 → 21 Jul 2006

Conference

Conference	International Joint Conference on Neural Networks 2006, IJCNN '06
Country/Territory	Canada
City	Vancouver, BC
Period	16/07/06 → 21/07/06

ASJC Scopus subject areas

Software

More information

http://hdl.handle.net/10397/1418

Cite this

@inproceedings{577301fb48d94cfda91949dc4bfb98a8,

title = "A variable node-to-node-link neural network and its application to hand-written recognition",

abstract = "This paper presents a variable node-to-node-link neural network (VN 2NN) trained by real-coded genetic algorithm (RCGA). The VN 2NN exhibits a node-to-node relationship in the hidden layer, and the network parameters are variable. These characteristics make the network adapt to the changes of the input environment, enable it to tackle different input sets distributed in a large domain. Each input data set is effectively handled by a corresponding set of network parameters. The set of parameters are governed by the other nodes. Taking the advantage of these features, the proposed network ensures better learning and generalization abilities. Application of the proposed network to hand-written graffiti recognition will be presented so as to illustrate the improvement.",

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

year = "2006",

month = dec,

day = "1",

language = "English",

isbn = "0780394909",

pages = "921--928",

booktitle = "International Joint Conference on Neural Networks 2006, IJCNN '06",

note = "International Joint Conference on Neural Networks 2006, IJCNN '06 ; Conference date: 16-07-2006 Through 21-07-2006",

}

A variable node-to-node-link neural network and its application to hand-written recognition. / Ling, S. H.; Leung, Hung Fat Frank; Lam, H. K.
International Joint Conference on Neural Networks 2006, IJCNN '06. 2006. p. 921-928 1716195.

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

TY - GEN

T1 - A variable node-to-node-link neural network and its application to hand-written recognition

AU - Ling, S. H.

AU - Leung, Hung Fat Frank

AU - Lam, H. K.

PY - 2006/12/1

Y1 - 2006/12/1

N2 - This paper presents a variable node-to-node-link neural network (VN 2NN) trained by real-coded genetic algorithm (RCGA). The VN 2NN exhibits a node-to-node relationship in the hidden layer, and the network parameters are variable. These characteristics make the network adapt to the changes of the input environment, enable it to tackle different input sets distributed in a large domain. Each input data set is effectively handled by a corresponding set of network parameters. The set of parameters are governed by the other nodes. Taking the advantage of these features, the proposed network ensures better learning and generalization abilities. Application of the proposed network to hand-written graffiti recognition will be presented so as to illustrate the improvement.

AB - This paper presents a variable node-to-node-link neural network (VN 2NN) trained by real-coded genetic algorithm (RCGA). The VN 2NN exhibits a node-to-node relationship in the hidden layer, and the network parameters are variable. These characteristics make the network adapt to the changes of the input environment, enable it to tackle different input sets distributed in a large domain. Each input data set is effectively handled by a corresponding set of network parameters. The set of parameters are governed by the other nodes. Taking the advantage of these features, the proposed network ensures better learning and generalization abilities. Application of the proposed network to hand-written graffiti recognition will be presented so as to illustrate the improvement.

UR - http://www.scopus.com/inward/record.url?scp=40649103205&partnerID=8YFLogxK

M3 - Conference article published in proceeding or book

SN - 0780394909

SN - 9780780394902

SP - 921

EP - 928

BT - International Joint Conference on Neural Networks 2006, IJCNN '06

T2 - International Joint Conference on Neural Networks 2006, IJCNN '06

Y2 - 16 July 2006 through 21 July 2006

ER -

A variable node-to-node-link neural network and its application to hand-written recognition

Abstract

Conference

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this