TY - JOUR
T1 - Competitive and dynamic cooperative learning algorithm
AU - Li, Tao
AU - Pei, Wen Jiang
AU - Wang, Shao Ping
AU - CHEUNG, Yiu Ming
N1 - Copyright:
Copyright 2010 Elsevier B.V., All rights reserved.
PY - 2010/1
Y1 - 2010/1
N2 - Although rival penalized competitive learning (RPCL) and its variants can select cluster numbers automatically, they have some important limitations. Based on the semi-competitive learning mechanism of competitive and cooperative learning (CCL), this paper presents a new robust dynamic cooperative learning algorithm, or competitive and dynamic cooperative learning (CDCL), in which the learning rate of each seed point within a cooperative team can be adaptively adjusted. CDCL not only inherits the merits of CCL, RPCL and its variants, but also overcomes most of their shortcomings. It is insensitive to the initialization of seed points and applicable to heterogeneous clusters with an attractive and accurate convergence property. Experiments on Gaussian mixture clustering and color image segmentation have shown the efficacy of CDCL. Moreover, in complex cases its performance was far superior to CCL and some other variants of RPCL.
AB - Although rival penalized competitive learning (RPCL) and its variants can select cluster numbers automatically, they have some important limitations. Based on the semi-competitive learning mechanism of competitive and cooperative learning (CCL), this paper presents a new robust dynamic cooperative learning algorithm, or competitive and dynamic cooperative learning (CDCL), in which the learning rate of each seed point within a cooperative team can be adaptively adjusted. CDCL not only inherits the merits of CCL, RPCL and its variants, but also overcomes most of their shortcomings. It is insensitive to the initialization of seed points and applicable to heterogeneous clusters with an attractive and accurate convergence property. Experiments on Gaussian mixture clustering and color image segmentation have shown the efficacy of CDCL. Moreover, in complex cases its performance was far superior to CCL and some other variants of RPCL.
KW - Clustering analysis
KW - Competitive and cooperative learning(CCL)
KW - Competitive and dynamic cooperative learning(CDCL)
KW - Rival peralized competitive learning(RPCL)
UR - http://www.scopus.com/inward/record.url?scp=77952133997&partnerID=8YFLogxK
U2 - 10.3969/j.issn.1006-7043.2010.01.018
DO - 10.3969/j.issn.1006-7043.2010.01.018
M3 - Journal article
AN - SCOPUS:77952133997
SN - 1006-7043
VL - 31
SP - 102
EP - 108
JO - Harbin Gongcheng Daxue Xuebao/Journal of Harbin Engineering University
JF - Harbin Gongcheng Daxue Xuebao/Journal of Harbin Engineering University
IS - 1
ER -