Title :
A learning rule for fuzzy associative memories
Author :
Junbo, Fan ; Fan, Jin ; Yan, Shi
Author_Institution :
Inst. of Neural Networks & Inf. Tech., Southwest Jiaotong Univ., Sichuan, China
fDate :
27 Jun-2 Jul 1994
Abstract :
In this paper, a learning rule for multiple pattern pairs in fuzzy associative memories (FAMs) with max-min composition units is presented. Under a certain condition, the proposed rule can efficiently encode multiple fuzzy pattern pairs in a single FAM and perfect association of these pairs can be achieved. The correctness of the proposed rule is proved and illustrative examples are given
Keywords :
associative processing; content-addressable storage; encoding; fuzzy neural nets; learning (artificial intelligence); matrix algebra; minimax techniques; pattern recognition; encoding; fuzzy associative memories; fuzzy neural network; learning rule; max-min composition units; multiple pattern pairs; weight matrix; Associative memory; Decision making; Encoding; Fuzzy control; Fuzzy logic; Fuzzy neural networks; Iterative algorithms; Neural networks; Pattern recognition; Power system modeling;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374953
