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.
Original language | English |
---|---|
Pages (from-to) | 1240-1241 |
Number of pages | 2 |
Journal | Electronics Letters |
Volume | 34 |
Issue number | 12 |
DOIs | |
Publication status | Published - 1998 Jun 11 |
Externally published | Yes |
ASJC Scopus subject areas
- Electrical and Electronic Engineering