An integrated algorithm of magnified gradient function and weight evolution for solving local minima problem

S. C. Ng; S. H. Leung; A. Luk

An integrated algorithm of magnified gradient function and weight evolution for solving local minima problem

S. C. Ng
, S. H. Leung
, A. Luk

Hong Kong Metropolitan University

Research output: Contribution to conference › Paper › peer-review

2 Citations (Scopus)

Abstract

This paper presents the integration of magnified gradient function and weight evolution algorithms in order to solve the local minima problem. The combination of the two algorithms will give a significant improvement in terms of convergence rate and global search capability as compared to some common fast learning algorithms such as the standard back-propagation, Quickprop, Resilent propagation (RPROP), SARPROP, and genetic algorithms (GA).

Original language	English
Pages	767-772
Number of pages	6
Publication status	Published - 2002
Event	2002 International Joint Conference on Neural Networks (IJCNN '02) - Honolulu, HI, United States Duration: 12 May 2002 → 17 May 2002

Conference

Conference	2002 International Joint Conference on Neural Networks (IJCNN '02)
Country/Territory	United States
City	Honolulu, HI
Period	12/05/02 → 17/05/02

Cite this

@conference{55cbca86b08c483ca4c310176e84ca3f,

title = "An integrated algorithm of magnified gradient function and weight evolution for solving local minima problem",

abstract = "This paper presents the integration of magnified gradient function and weight evolution algorithms in order to solve the local minima problem. The combination of the two algorithms will give a significant improvement in terms of convergence rate and global search capability as compared to some common fast learning algorithms such as the standard back-propagation, Quickprop, Resilent propagation (RPROP), SARPROP, and genetic algorithms (GA).",

author = "Ng, \{S. C.\} and Leung, \{S. H.\} and A. Luk",

year = "2002",

language = "English",

pages = "767--772",

note = "2002 International Joint Conference on Neural Networks (IJCNN '02) ; Conference date: 12-05-2002 Through 17-05-2002",

}

TY - CONF

T1 - An integrated algorithm of magnified gradient function and weight evolution for solving local minima problem

AU - Ng, S. C.

AU - Leung, S. H.

AU - Luk, A.

PY - 2002

Y1 - 2002

N2 - This paper presents the integration of magnified gradient function and weight evolution algorithms in order to solve the local minima problem. The combination of the two algorithms will give a significant improvement in terms of convergence rate and global search capability as compared to some common fast learning algorithms such as the standard back-propagation, Quickprop, Resilent propagation (RPROP), SARPROP, and genetic algorithms (GA).

AB - This paper presents the integration of magnified gradient function and weight evolution algorithms in order to solve the local minima problem. The combination of the two algorithms will give a significant improvement in terms of convergence rate and global search capability as compared to some common fast learning algorithms such as the standard back-propagation, Quickprop, Resilent propagation (RPROP), SARPROP, and genetic algorithms (GA).

UR - https://www.scopus.com/pages/publications/0036076599

M3 - Paper

AN - SCOPUS:0036076599

SP - 767

EP - 772

T2 - 2002 International Joint Conference on Neural Networks (IJCNN '02)

Y2 - 12 May 2002 through 17 May 2002

ER -

An integrated algorithm of magnified gradient function and weight evolution for solving local minima problem

Abstract

Conference

Other files and links

Fingerprint

Cite this