On information characteristics of sparsely encoded binary auto-associative memory

Author

Frolov, Alexander ; Rachkovskij, Dmitri ; Husek, Dusan

Author_Institution

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

Volume

1

fYear

2002

fDate

18-22 Nov. 2002

Firstpage

235

Abstract

A sparsely encoded Willshaw-like attractor neural network based on binary Hebbian synapses is investigated analytically and by computer simulations. A special inhibition mechanism which supports a constant number of active neurons at each time step is used. Informational capacity and size of attraction basins are evaluated for the single-step and the Gibson-Robinson approximations, as well as for experimental results.

Keywords

approximation theory; content-addressable storage; neural nets; Gibson-Robinson approximation; Willshaw-like attractor neural network; active neurons; attraction basins; binary Hebbian synapses; information characteristics; informational capacity; inhibition mechanism; single-step approximations; sparsely encoded binary auto-associative memory; Computer science; Computer simulation; Error analysis; Hopfield neural networks; Information analysis; Information technology; Intelligent networks; Neural networks; Neurons; Neurophysiology;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Information Processing, 2002. ICONIP '02. Proceedings of the 9th International Conference on

Print_ISBN

981-04-7524-1

Type

conf

DOI

10.1109/ICONIP.2002.1202168

Filename

1202168