Title :
A novel adaptive pattern recognition model with sparse associative memory networks
Author :
Guoqing, Yang ; Songcan, Chen ; Jun, Lu ; Chuan, Liu
Author_Institution :
Nanjing Aeronaut. Inst., China
Abstract :
On the basis of WISARD (an n-tuple adaptive pattern recognition system) and SDM (sparse distributed memory) models, the authors suggest a novel two-layered adaptive system in which the n-tuple recognition principle in WISARD is still followed and RAMs are n-tuple size in a larger range without the limitation of the cost. Experiments on Chinese character recognition have shown the feasibility of the model
Keywords :
adaptive systems; character recognition; content-addressable storage; neural nets; Chinese character recognition; WISARD; n-tuple adaptive pattern recognition system; neural nets; sparse associative memory networks; sparse distributed memory; Adaptive systems; Associative memory; Character recognition; Costs; Hopfield neural networks; Logic functions; Neural networks; Pattern recognition; Random access memory; Read-write memory;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170588
