DocumentCode :
2971468
Title :
An extended BAM neural network model
Author :
Zhenjiang, Miao ; Baozong, Yuan
Author_Institution :
Inst. of Inf. Sci., Northern Jiaotong Univ., Beijing, China
Volume :
3
fYear :
1993
fDate :
25-29 Oct. 1993
Firstpage :
2682
Abstract :
Proposes an extended bidirectional associative memory (BAM) neural network model which can do auto- and hetero-associative memory. The theoretical proof for this neural network model´s stability is given. Experiments show that this neural network model is much more powerful than the M-P model, discrete Hopfield neural network, continuous Hopfield neural network, discrete bidirectional associative memory neural network, continuous and adaptive bidirectional associative memory neural network, backpropagation neural network and optimal designed nonlinear continuous neural network. Experimental results also show that, when it does auto-associative memory, the power of this model is the same as the loop neural network model which can only do auto-associative memory.
Keywords :
content-addressable storage; neural nets; M-P model; auto-associative memory; backpropagation neural network; continuous Hopfield neural network; discrete Hopfield neural network; discrete bidirectional associative memory neural network; extended BAM neural network model; extended bidirectional associative memory neural network; hetero-associative memory; model stability; optimal designed nonlinear continuous neural network; Adaptive systems; Artificial neural networks; Associative memory; Hopfield neural networks; Information science; Intelligent control; Magnesium compounds; Neural networks; Neurofeedback; Stability;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on
Print_ISBN :
0-7803-1421-2
Type :
conf
DOI :
10.1109/IJCNN.1993.714276
Filename :
714276
Link To Document :
بازگشت