DocumentCode :
2630264
Title :
Hopfield network with O(N) complexity using a constrained backpropagation learning
Author :
Martinelli, G. ; Prefetti, R.
Author_Institution :
INFO-COM Dept., Rome Univ., Italy
fYear :
1991
fDate :
18-21 Nov 1991
Firstpage :
1464
Abstract :
A novel associative memory model is presented, which is derived from the Hopfield discrete neural network. Its architecture is greatly simplified because the number of interconnections grows only linearly with the dimensionality of the stored patterns. It makes use of a modified backpropagation algorithm as a learning tool. During the retrieval phase the network operates as an autoassociative BAM (directional associative memory), which searches for a minimum of an appropriate energy function. Computer simulations point out the good performances of the proposed learning method in terms of capacity and number of spurious stable states
Keywords :
computational complexity; content-addressable storage; learning systems; neural nets; Hopfield discrete neural network; O(N) complexity; autoassociative BAM; constrained backpropagation learning; content addressable storage; directional associative memory; learning method; Associative memory; Backpropagation algorithms; Computer simulation; Hardware; Hopfield neural networks; Learning systems; Magnesium compounds; Neural networks; Neurons; Probes;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
Type :
conf
DOI :
10.1109/IJCNN.1991.170606
Filename :
170606
Link To Document :
بازگشت