Raport Badawczy = Research Report ; RB/29/2004
Instytut Badań Systemowych. Polska Akademia Nauk ; Systems Research Institute. Polish Academy of Sciences
24 pages ; 21 cm ; Bibliography p. 21-24
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.
Raport Badawczy = Research Report
Creative Commons Attribution BY 4.0 license
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: ; -
Systems Research Institute of the Polish Academy of Sciences
Library of Systems Research Institute PAS
19 paź 2021
17 wrz 2020
29
https://rcin.org.pl./publication/175021
Nazwa wydania | Data |
---|---|
RB-2004-29 : Wilbik Anna : Genetic algorithms in learning methods of associative memory | 19 paź 2021 |
Gorączko, Marcin Cichowska, Jolanta
Stańczak, Jarosław
Novotny, Antonio Szulc, Katarzyna Żochowski, Antoni
Grądzki, Piotr
Kacprzyk, Janusz (1947– ) Wilbik, Anna
Kacprzyk, Janusz (1947– ) Wilbik, Anna