DocumentCode
2496689
Title
Investigation of generalized Hopfield model by statistical physics methods
Author
Kryzhanovsky, Boris V. ; Litinskii, Leonid B.
Author_Institution
Center of Opt. Neural Technol., Russian Acad. of Sci., Moscow, Russia
fYear
2010
fDate
18-23 July 2010
Firstpage
1
Lastpage
6
Abstract
The proposed generalization of the Hopfield model consists in assigning different weight coefficients to input patterns that are used to construct the Hebb connection matrix. Application of statistical physics methods to such a system gives unexpected results even for the simplest variant of differences of weight coefficients. Namely, there are unusual behaviors of the critical value of the load parameter and of the overlap of the state with the pattern.
Keywords
Hopfield neural nets; generalisation (artificial intelligence); matrix algebra; statistical analysis; Hebb connection matrix; generalized Hopfield model; statistical physics methods; Analytical models; Associative memory; Character recognition; Equations; Mathematical model; Physics;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks (IJCNN), The 2010 International Joint Conference on
Conference_Location
Barcelona
ISSN
1098-7576
Print_ISBN
978-1-4244-6916-1
Type
conf
DOI
10.1109/IJCNN.2010.5596872
Filename
5596872
Link To Document