Title:

Genetic algorithms in learning methods of associative memory

Subtitle:

Raport Badawczy = Research Report ; RB/29/2004

Creator:

Wilbik, Anna

Publisher:

Instytut Badań Systemowych. Polska Akademia Nauk ; Systems Research Institute. Polish Academy of Sciences

Place of publishing:

Warszawa

Date issued/created:

2004

Description:

24 pages ; 21 cm ; Bibliography p. 21-24

Subject and Keywords:

Genetic algorithm ; Hopfields model ; Storage capacity ; Basin of attraction

Abstract:

In this paper the Hopfield neural network model of associative memory that uses evolutionary approach as a learning method is analyzed. Several types of genetic algorithms will be investigated. In resulting networks quality measures (such as storage capacity, error correcting capabilities and the usage of additional knowledge) will be carefully examined. The basic criterion for algorithm’s evaluation is the storage capacity. The well-known Hebbian rule provides the capacity to be 15% of the number of the neurons. It has been shown that genetic algorithms allow us to improve this result.

Relation:

Raport Badawczy = Research Report

Resource type:

Text

Detailed Resource Type:

Report

Source:

RB-2004-29

Language:

eng

Language of abstract:

eng

Rights:

Creative Commons Attribution BY 4.0 license

Terms of use:

Copyright-protected material. [CC BY 4.0] May be used within the scope specified in Creative Commons Attribution BY 4.0 license, full text available at: ; -

Digitizing institution:

Systems Research Institute of the Polish Academy of Sciences

Original in:

Library of Systems Research Institute PAS

Projects co-financed by:

Operational Program Digital Poland, 2014-2020, Measure 2.3: Digital accessibility and usefulness of public sector information; funds from the European Regional Development Fund and national co-financing from the state budget.

Access:

Open