Title :
Learning method for fuzzy ARTMAP in a noisy environment
Author :
Lee, J.S. ; Yoon, C.G. ; Lee, C.W.
Author_Institution :
Coll. of Eng., Seoul Nat. Univ., South Korea
fDate :
1/8/1998 12:00:00 AM
Abstract :
A new learning method is proposed to enhance the performances of fuzzy adaptive resonance theory-predictive mapping (ARTMAP) neural networks in a noisy environment. It combines the average learning and slow learning for the weight vectors in fuzzy ARTMAP. It effectively reduces a category proliferation problem, and enhances recognition performance for noisy input patterns
Keywords :
ART neural nets; category theory; fuzzy neural nets; learning (artificial intelligence); pattern recognition; adaptive resonance theory-predictive mapping; average learning; category proliferation; fuzzy ARTMAP neural network; noisy environment; pattern recognition; slow learning; weight vectors;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19980004
