Deterministic weight evolution algorithm for solving local minima problem

Sin-Chun Ng; Chi-Chung Cheung; Shu-Hung Leung

doi:10.1049/el:20000747

Deterministic weight evolution algorithm for solving local minima problem

Sin-Chun Ng, Chi-Chung Cheung, Shu-Hung Leung

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

7 Citations (Scopus)

Abstract

The behavior of the weight evolution algorithm with deterministic perturbation is presented. The new algorithm evolves the innermost layer of weights in order to escape from local minima. Simulation results have shown that the use of weight evolution with deterministic perturbation leads to an increase in the global convergence percentage, as compared with other traditional methods.

Original language	English
Pages (from-to)	1039-1041
Journal	Electronics Letters
Volume	36
Issue number	12
DOIs	https://doi.org/10.1049/el:20000747
Publication status	Published - 8 Jun 2000

Access Output

10.1049/el:20000747

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{d6ba5897727e4c4ba107cbb3c10a5531,

title = "Deterministic weight evolution algorithm for solving local minima problem",

abstract = "The behavior of the weight evolution algorithm with deterministic perturbation is presented. The new algorithm evolves the innermost layer of weights in order to escape from local minima. Simulation results have shown that the use of weight evolution with deterministic perturbation leads to an increase in the global convergence percentage, as compared with other traditional methods.",

author = "Sin-Chun Ng and Chi-Chung Cheung and Shu-Hung Leung",

year = "2000",

month = jun,

day = "8",

doi = "10.1049/el:20000747",

language = "English",

volume = "36",

pages = "1039--1041",

journal = "Electronics Letters",

issn = "0013-5194",

publisher = "John Wiley & Sons",

number = "12",

}

TY - JOUR

T1 - Deterministic weight evolution algorithm for solving local minima problem

AU - Ng, Sin-Chun

AU - Cheung, Chi-Chung

AU - Leung, Shu-Hung

PY - 2000/6/8

Y1 - 2000/6/8

N2 - The behavior of the weight evolution algorithm with deterministic perturbation is presented. The new algorithm evolves the innermost layer of weights in order to escape from local minima. Simulation results have shown that the use of weight evolution with deterministic perturbation leads to an increase in the global convergence percentage, as compared with other traditional methods.

AB - The behavior of the weight evolution algorithm with deterministic perturbation is presented. The new algorithm evolves the innermost layer of weights in order to escape from local minima. Simulation results have shown that the use of weight evolution with deterministic perturbation leads to an increase in the global convergence percentage, as compared with other traditional methods.

UR - http://www.scopus.com/inward/record.url?scp=0033715329&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-0033715329&origin=recordpage

U2 - 10.1049/el:20000747

DO - 10.1049/el:20000747

M3 - RGC 21 - Publication in refereed journal

SN - 0013-5194

VL - 36

SP - 1039

EP - 1041

JO - Electronics Letters

JF - Electronics Letters

IS - 12

ER -

Deterministic weight evolution algorithm for solving local minima problem

Abstract

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this