Deterministic weight modification algorithm for efficient learning

S. C. Ng; C. C. Cheung; S. H. Leung

doi:10.1109/IJCNN.2004.1380076

Deterministic weight modification algorithm for efficient learning

S. C. Ng, C. C. Cheung, S. H. Leung

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

Abstract

This paper presents a new approach using deterministic weight modification (DWM) to speed up the convergence rate effectively and improve the global convergence capability of the standard and modified back-propagation (BP) algorithms. The main idea of DWM is to reduce the system error by changing the weights of a multi-layered feed-forward neural network in a deterministic way. Simulation results show that the performance of DWM is better than BP and other modified BP algorithms for a number of learning problems.

Original language	English
Title of host publication	2004 IEEE International Joint Conference on Neural Networks - Proceedings
Pages	1033-1038
Number of pages	6
DOIs	https://doi.org/10.1109/IJCNN.2004.1380076
Publication status	Published - 25 Jul 2004
Externally published	Yes
Event	2004 IEEE International Joint Conference on Neural Networks - Proceedings - Budapest, Hungary Duration: 25 Jul 2004 → 29 Jul 2004

Publication series

Name	IEEE International Conference on Neural Networks - Conference Proceedings
Volume	2
ISSN (Print)	1098-7576

Conference

Conference	2004 IEEE International Joint Conference on Neural Networks - Proceedings
Country/Territory	Hungary
City	Budapest
Period	25/07/04 → 29/07/04

ASJC Scopus subject areas

Software

More information

10.1109/IJCNN.2004.1380076

Cite this

@inproceedings{585db48a3b384338875f06b3d506af5e,

title = "Deterministic weight modification algorithm for efficient learning",

abstract = "This paper presents a new approach using deterministic weight modification (DWM) to speed up the convergence rate effectively and improve the global convergence capability of the standard and modified back-propagation (BP) algorithms. The main idea of DWM is to reduce the system error by changing the weights of a multi-layered feed-forward neural network in a deterministic way. Simulation results show that the performance of DWM is better than BP and other modified BP algorithms for a number of learning problems.",

author = "Ng, {S. C.} and Cheung, {C. C.} and Leung, {S. H.}",

year = "2004",

month = jul,

day = "25",

doi = "10.1109/IJCNN.2004.1380076",

language = "English",

isbn = "0780383591",

series = "IEEE International Conference on Neural Networks - Conference Proceedings",

pages = "1033--1038",

booktitle = "2004 IEEE International Joint Conference on Neural Networks - Proceedings",

note = "2004 IEEE International Joint Conference on Neural Networks - Proceedings ; Conference date: 25-07-2004 Through 29-07-2004",

}

Ng, SC, Cheung, CC & Leung, SH 2004, Deterministic weight modification algorithm for efficient learning. in 2004 IEEE International Joint Conference on Neural Networks - Proceedings. IEEE International Conference on Neural Networks - Conference Proceedings, vol. 2, pp. 1033-1038, 2004 IEEE International Joint Conference on Neural Networks - Proceedings, Budapest, Hungary, 25/07/04. https://doi.org/10.1109/IJCNN.2004.1380076

Deterministic weight modification algorithm for efficient learning. / Ng, S. C.; Cheung, C. C.; Leung, S. H.
2004 IEEE International Joint Conference on Neural Networks - Proceedings. 2004. p. 1033-1038 (IEEE International Conference on Neural Networks - Conference Proceedings; Vol. 2).

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

TY - GEN

T1 - Deterministic weight modification algorithm for efficient learning

AU - Ng, S. C.

AU - Cheung, C. C.

AU - Leung, S. H.

PY - 2004/7/25

Y1 - 2004/7/25

N2 - This paper presents a new approach using deterministic weight modification (DWM) to speed up the convergence rate effectively and improve the global convergence capability of the standard and modified back-propagation (BP) algorithms. The main idea of DWM is to reduce the system error by changing the weights of a multi-layered feed-forward neural network in a deterministic way. Simulation results show that the performance of DWM is better than BP and other modified BP algorithms for a number of learning problems.

AB - This paper presents a new approach using deterministic weight modification (DWM) to speed up the convergence rate effectively and improve the global convergence capability of the standard and modified back-propagation (BP) algorithms. The main idea of DWM is to reduce the system error by changing the weights of a multi-layered feed-forward neural network in a deterministic way. Simulation results show that the performance of DWM is better than BP and other modified BP algorithms for a number of learning problems.

UR - http://www.scopus.com/inward/record.url?scp=10944246598&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2004.1380076

DO - 10.1109/IJCNN.2004.1380076

M3 - Conference article published in proceeding or book

AN - SCOPUS:10944246598

SN - 0780383591

T3 - IEEE International Conference on Neural Networks - Conference Proceedings

SP - 1033

EP - 1038

BT - 2004 IEEE International Joint Conference on Neural Networks - Proceedings

T2 - 2004 IEEE International Joint Conference on Neural Networks - Proceedings

Y2 - 25 July 2004 through 29 July 2004

ER -

Deterministic weight modification algorithm for efficient learning

Abstract

Publication series

Conference

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this