Convergence time in Hopfield network

Author

Frolov, A.A. ; Husek, D.

Author_Institution

Inst. of Higher Nervous Activity & Neurophysiol., Acad. of Sci., Moscow

Volume

5

fYear

2000

fDate

2000

Firstpage

622

Abstract

Convergence time in Hopfield attractor neural network with parallel dynamics is investigated by computer simulation of networks of extremely large size (up to the number of neurons N=10⁵). A special algorithm is used to avoid storage in the computer memory of both connection matrix and the set of stored prototypes. Thus, the size of the simulated network is restricted only by the processing time. It is shown that asymptotically for N→∞ the number of time steps S which are required to reach the attractor in the vicinity of the recalled prototype is proportional to N^γ where power index γ≪1

Keywords

Hopfield neural nets; computational complexity; convergence; virtual machines; Hopfield attractor neural network; computer memory; computer simulation; connection matrix; convergence time; parallel dynamics; power index; processing time; recalled prototype; simulated network; special algorithm; stored prototypes; Computational modeling; Computer networks; Computer simulation; Convergence; Hopfield neural networks; Intelligent networks; Neural networks; Neurons; Prototypes; Virtual prototyping;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on

Conference_Location

Como

ISSN

1098-7576

Print_ISBN

0-7695-0619-4

Type

conf

DOI

10.1109/IJCNN.2000.861538

Filename

861538