Unsupervised fuzzy competitive learning with monotonically decreasing fuzziness

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

2 Citations (Scopus)

Abstract

Despite of its simplicity and success in various applications, conventional competitive learning (CL) taking use of the winner-take-all strategy suffers from two major shortcomings, i.e. neuron underutilization and waste of closeness information computed. In this paper, a fuzzy approach to address these shortcomings is pursued. By considering the concept `win' as a fuzzy set, two existing competitive learning algorithms namely the standard CL algorithm and the frequency sensitive CL algorithm are generalized and the resulting fuzzy algorithms are proposed. Furthermore, a monotonically decreasing implementation scheme for the fuzziness parameter introduced in the proposed algorithms is suggested to further enhance the overall performance of the fuzzy algorithms. The effectiveness of the proposed algorithms is demonstrated with numerical examples.
Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
PublisherPubl by IEEE
Pages2929-2932
Number of pages4
Volume3
ISBN (Print)0780314212, 9780780314214
Publication statusPublished - 1 Dec 1993
Externally publishedYes
EventProceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3) - Nagoya, Japan
Duration: 25 Oct 199329 Oct 1993

Conference

ConferenceProceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3)
CountryJapan
CityNagoya
Period25/10/9329/10/93

ASJC Scopus subject areas

  • Engineering(all)

Cite this