Title :
Loop neural network model for associative memory
Author :
Miao Zhenjiang ; Yuan Baozong
Author_Institution :
Inst. of Inf. Sci., Northern Jiaotong Univ., Beijing, China
Abstract :
Proposes a new associative memory neural net (NN) model called the loop neural network model, and the theoretical proof of this NN´s stability is given. Experiments show that this NN model is much more powerful than the McCulloch-Pitts model, the discrete Hopfield NN, the continuous Hopfield NN, the discrete bidirectional associative memory NN, the continuous and adaptive bidirectional associative memory NN, the backpropagation NN, and the optimally designed nonlinear continuous NN.<>
Keywords :
content-addressable storage; neural nets; stability; McCulloch-Pitts model; backpropagation neural net; continuous Hopfield neural net; continuous adaptive bidirectional associative memory neural net; discrete Hopfield neural net; discrete bidirectional associative memory neural net; loop neural network model; optimally designed nonlinear continuous neural net; stability; Artificial neural networks; Associative memory; Differential equations; Hopfield neural networks; Information science; Learning; Multi-layer neural network; Neural networks; Neurons; Stability;
Conference_Titel :
TENCON '93. Proceedings. Computer, Communication, Control and Power Engineering.1993 IEEE Region 10 Conference on
Conference_Location :
Beijing, China
Print_ISBN :
0-7803-1233-3
DOI :
10.1109/TENCON.1993.320076
