Title :
Fast design algorithm for competitive learning
Author :
Hwang, Wen-Jyi ; Lin, Faa-Jeng ; Zeng, Yi-Chong
Author_Institution :
Dept. of Electr. Eng., Chung Yuan Christian Univ., Chung Li, Taiwan
fDate :
8/14/1997 12:00:00 AM
Abstract :
The authors present a new, fast computation algorithm which significantly reduces the training time of the competitive learning (CL) algorithm without sacrificing its performance. The training process is performed in the wavelet domain to identify the winning neural units with a small number of multiplications. Simulation results show that in many cases the algorithm requires <10% of the computational time required by traditional CL algorithms
Keywords :
neural nets; unsupervised learning; wavelet transforms; competitive learning; computation algorithm; computational time; multiplications; training time; wavelet domain; winning neural units;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19971010
