On informational characteristics of Willshaw-like auto-associative memory

Title:

On informational characteristics of Willshaw-like auto-associative memory

Creator:

Frolov, A. A., Rachkovskij, D. A., and Husek, D.

Identifier:

https://cdk.lib.cas.cz/client/handle/uuid:c823c464-b756-49fb-9c25-4ada3debecf8
uuid:c823c464-b756-49fb-9c25-4ada3debecf8

Subject:

Willshaw-like, sparse encoding, attractor neural network, binary Hebbian synapses, computer simulations, constant, informational capacity, attraction basins size, Single-Step approximation, and Gibson-Robinson approximation

Type:

model:article and TEXT

Format:

bez média and svazek

Description:

A sparsely encoded Willshaw-like attractor neural network based on the 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. The informationg capacity and the size of attraction basins are evaluated for the Single-Step and the Gibson-Robinson approximations, as well as for experimental results.

Language:

English

Rights:

http://creativecommons.org/publicdomain/mark/1.0/
policy:public

Source:

Neural network world: international journal on neural and mass-parallel computing and information systems | 2002 Volume:12 | Number:2

Harvested from:

CDK

Metadata only:

false