Title :
Fuzzy competitive learning algorithm with decreasing fuzziness
Author :
Chung, Fu-Lai ; Lee, Taewoo
Author_Institution :
Chinese Univ. of Hong Kong, Shatin, Hong Kong
fDate :
6/24/1993 12:00:00 AM
Abstract :
A competitive learning algorithm with the concept ´winner´ modelled by a fuzzy set is presented. Additionally, an implementation scheme for the fuzziness parameter introduced is suggested to further enhance the algorithm´s performance in avoiding neuron underuse and converging to optimal cluster centroids.
Keywords :
fuzzy set theory; learning (artificial intelligence); neural nets; competitive learning algorithm; fuzziness parameter; fuzzy set; optimal cluster centroids;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19930806