DocumentCode
387554
Title
Several symmetry properties of discrete Hopfield neural networks
Author
Dong, Ji-Yang ; Zhang, Jun-Ying
Author_Institution
Nat. Key Lab. for Radar Signal Process., Xidian Univ., Xi´´an, China
Volume
3
fYear
2002
fDate
2002
Firstpage
1374
Abstract
Symmetry is powerful tool to reduce the freedom of a problem. Discrete Hopfield neural networks with Hebbian learning are studied by the method of group theory in this paper, and several symmetry properties of the network being an auto-associator are given and proved.
Keywords
Hebbian learning; Hopfield neural nets; group theory; symmetry; Hebbian learning; auto-associator; discrete Hopfield neural networks; group theory; symmetry properties; Associative memory; DH-HEMTs; Hamming distance; Hebbian theory; Hopfield neural networks; Hypercubes; Neural networks; Neurons; Radar signal processing; State-space methods;
fLanguage
English
Publisher
ieee
Conference_Titel
Machine Learning and Cybernetics, 2002. Proceedings. 2002 International Conference on
Print_ISBN
0-7803-7508-4
Type
conf
DOI
10.1109/ICMLC.2002.1167431
Filename
1167431
Link To Document