Title :
Convergence analysis of rival penalized competitive learning (RPCL) algorithm
Author :
Ma, Jinwen ; Wang, Taijun ; Xu, Lei
Author_Institution :
Dept. of Comput. Sci., Chinese Univ. of Hong Kong, Shatin, China
fDate :
6/24/1905 12:00:00 AM
Abstract :
This paper analyzes the convergence of the rival penalized competitive learning (RPCL) algorithm via a cost function. It is shown that as RPCL process decreases the cost to a global minimum, a correct number of weight vectors will converge to each center of the clusters in the sample data respectively, while the others diverge
Keywords :
convergence; neural nets; optimisation; unsupervised learning; competitive learning network; convergence; cost function; local minimum; rival penalized competitive learning; sample data; weight vectors; Algorithm design and analysis; Clustering algorithms; Computer science; Convergence; Cost function; H infinity control; Information analysis; Information science; Laboratories; Power capacitors;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1007756
