Evolution strategies on connection weights into modified gradient function for multi-layer neural networks

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

doi:10.1109/IJCNN.2005.1556074

Evolution strategies on connection weights into modified gradient function for multi-layer neural networks

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

Hong Kong Metropolitan University

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

1 Citation (Scopus)

Abstract

In this paper, two modifications on the conventional back-propagation algorithm for feedforward multi-layer neural networks are presented. One modification is based on the calculation of the gradient function, while the other one is the use of evolution strategies on connection weights into the gradient search algorithm. From simulation results, the new modified algorithm always converges to the global optimal solution with better performance when compared with other fast learning algorithms and global search methods.

Original language	English
Pages	1371-1376
Number of pages	6
DOIs	https://doi.org/10.1109/IJCNN.2005.1556074
Publication status	Published - 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

Access to Document

10.1109/IJCNN.2005.1556074

Cite this

@conference{8d07238f99934244955c47f105695d86,

title = "Evolution strategies on connection weights into modified gradient function for multi-layer neural networks",

abstract = "In this paper, two modifications on the conventional back-propagation algorithm for feedforward multi-layer neural networks are presented. One modification is based on the calculation of the gradient function, while the other one is the use of evolution strategies on connection weights into the gradient search algorithm. From simulation results, the new modified algorithm always converges to the global optimal solution with better performance when compared with other fast learning algorithms and global search methods.",

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

year = "2005",

doi = "10.1109/IJCNN.2005.1556074",

language = "English",

pages = "1371--1376",

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

}

TY - CONF

T1 - Evolution strategies on connection weights into modified gradient function for multi-layer neural networks

AU - Ng, S. C.

AU - Leung, S. H.

AU - Luk, Andrew

PY - 2005

Y1 - 2005

N2 - In this paper, two modifications on the conventional back-propagation algorithm for feedforward multi-layer neural networks are presented. One modification is based on the calculation of the gradient function, while the other one is the use of evolution strategies on connection weights into the gradient search algorithm. From simulation results, the new modified algorithm always converges to the global optimal solution with better performance when compared with other fast learning algorithms and global search methods.

AB - In this paper, two modifications on the conventional back-propagation algorithm for feedforward multi-layer neural networks are presented. One modification is based on the calculation of the gradient function, while the other one is the use of evolution strategies on connection weights into the gradient search algorithm. From simulation results, the new modified algorithm always converges to the global optimal solution with better performance when compared with other fast learning algorithms and global search methods.

UR - http://www.scopus.com/inward/record.url?scp=33750134607&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2005.1556074

DO - 10.1109/IJCNN.2005.1556074

M3 - Paper

AN - SCOPUS:33750134607

SP - 1371

EP - 1376

T2 - International Joint Conference on Neural Networks, IJCNN 2005

Y2 - 31 July 2005 through 4 August 2005

ER -

Evolution strategies on connection weights into modified gradient function for multi-layer neural networks

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this