Title :
Competitive learning with subspace search in transform domain
Author_Institution :
Dept. of Electr. Eng., Chung Yuan Christian Univ., Chung Li
fDate :
6/11/1998 12:00:00 AM
Abstract :
A new competitive learning (CL) algorithm with k-winners-take-all activation is presented. The k winning neurons for updating are those best matching the input vector in the wavelet domain with subspace search. Simulation results show that the algorithm gives a better performance than that of the traditional CL algorithm while requiring much less computational time
Keywords :
image coding; neural nets; unsupervised learning; vector quantisation; wavelet transforms; VQ; competitive learning; computational time; input vector; k-winners-take-all activation; subspace search; transform domain; updating; wavelet domain;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19980858
