Binary factorization in Hopfield-like neural networks: single-step approximation and computer simulations

Title:

Binary factorization in Hopfield-like neural networks: single-step approximation and computer simulations

Creator:

Frolov, A. A., Sirota, A. M., Húsek, D., Muraviev, I. P., and Polyakov, P. A.

Identifier:

https://cdk.lib.cas.cz/client/handle/uuid:697cc5dc-013b-4ce3-b90a-b05b14a13906
uuid:697cc5dc-013b-4ce3-b90a-b05b14a13906

Subject:

nonlinear binary factor analysis, feature extraction, recurrent neural network, Single-Step approximation, neurodynamics simulation, attraction basins, Hebbian learning, unsupervised learning, neuroscience, and brain functions modeling

Type:

model:article and TEXT

Format:

bez média and svazek

Description:

The unsupervised learning of feature extraction in high-dimesional patterns is a central problem for the neural network approach. Feature extraction is a procedure which maps original patterns into the feature (or factor) space of reduced dimension. In this paper we demonstrate that Hebbian learning in Hopfield-like neural network is a natural procedure for unsupervised learning of feature extraction. Due to this learning, factors become the attractors of network dynamics, hence they can be revealed by the random search. The neurodynamics is analysed by Single-Step approximation which is known [8] to be rather accurate for sparsely encoded Hopfield-network. Thus, the analysis is restricted by the case of sparsely encoded factors. The accuracy of Single-Step approximation is confirmed by Computer simulations.

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 | 2004 Volume:14 | Number:2

Harvested from:

CDK

Metadata only:

false