Deterministic weight evolution algorithm for solving local minima problem

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

7 Scopus Citations
Scopus Metrics
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)1039-1041
Journal / PublicationElectronics Letters
Volume36
Issue number12
Publication statusPublished - 8 Jun 2000

Link(s)

DOI

DOI
Check@CityULib
Link to Scopus https://www.scopus.com/record/display.uri?eid=2-s2.0-0033715329&origin=recordpage
Permanent Link https://scholars.cityu.edu.hk/en/publications/publication(d6ba5897-727e-4c4b-a107-cbb3c10a5531).html

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.

Fingerprint

Publication fingerprints text

100
Weight Mathematics
100
Local Minimum Mathematics
100
Algorithm Mathematics
100
Algorithms Computer Science
100
Weight Evolution Keyphrases
100
Deterministic Weigh... Keyphrases
100
Local Minimum Probl... Keyphrases
100
Evolution Algorithm Keyphrases
100
algorithms INIS
100
weight INIS
Full Fingerprint ›

Citation Format(s)

[ RIS ] [ BibTeX ]
Deterministic weight evolution algorithm for solving local minima problem. / Ng, Sin-Chun; Cheung, Chi-Chung; Leung, Shu-Hung.
In: Electronics Letters, Vol. 36, No. 12, 08.06.2000, p. 1039-1041.

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