Geodesic
Evolutionary approach to creating a neural network
News of the Kabardin-Balkar scientific center of RAS, no. 5 (2015), pp. 24-30.

Voir la notice de l'article provenant de la source Math-Net.Ru

The article examines the possibility of using an evolutionary approach to improve implementation of neural networks and self-learning mechanisms for solving problems based on multi-agent representation of knowledge. The collective use of artificial neural networks as a neural network of agents can further parallelize and distribute between local agents the processes of solving complex intellectual tasks. The algorithms of integrated evolutionary search of the weights to solve a number of learning objectives are described. We propose a genetic algorithm, generating neural network model of optimal topology. In the present genetic algorithm each individual represents a separate neural network, and the population is considered as an evolving multi-agent system in which the strategy of behavior of each agent is determined by its corresponding neural network.
Keywords: decision support system; evolutionary modeling; genetic algorithm; artificial neural networks; multi-agent system; neural network model; intelligent agent. 
@article{IZKAB_2015_5_a3,
     author = {M. I. Anchekov and V. V. Bova and O. V. Nagoeva and A. A. Novikov and I. A. Pshenokova},
     title = {Evolutionary approach to creating a neural network},
     journal = {News of the Kabardin-Balkar scientific center of RAS},
     pages = {24--30},
     publisher = {mathdoc},
     number = {5},
     year = {2015},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/IZKAB_2015_5_a3/}
}
TY  - JOUR
AU  - M. I. Anchekov
AU  - V. V. Bova
AU  - O. V. Nagoeva
AU  - A. A. Novikov
AU  - I. A. Pshenokova
TI  - Evolutionary approach to creating a neural network
JO  - News of the Kabardin-Balkar scientific center of RAS
PY  - 2015
SP  - 24
EP  - 30
IS  - 5
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/IZKAB_2015_5_a3/
LA  - ru
ID  - IZKAB_2015_5_a3
ER  - 
%0 Journal Article
%A M. I. Anchekov
%A V. V. Bova
%A O. V. Nagoeva
%A A. A. Novikov
%A I. A. Pshenokova
%T Evolutionary approach to creating a neural network
%J News of the Kabardin-Balkar scientific center of RAS
%D 2015
%P 24-30
%N 5
%I mathdoc
%U http://geodesic.mathdoc.fr/item/IZKAB_2015_5_a3/
%G ru
%F IZKAB_2015_5_a3
M. I. Anchekov; V. V. Bova; O. V. Nagoeva; A. A. Novikov; I. A. Pshenokova. Evolutionary approach to creating a neural network. News of the Kabardin-Balkar scientific center of RAS, no. 5 (2015), pp. 24-30. http://geodesic.mathdoc.fr/item/IZKAB_2015_5_a3/

[1] D. Yu. Zaporozhets, Yu. A. Kravchenko, A. A. Lezhebokov, “Sposoby intellektualnogo analiza dannykh v slozhnykh sistemakh”, Izvestiya Kabardino-Balkarskogo nauchnogo tsentra RAN, 2012, no. 3, 52–57

[2] A. N. Dukkardt, L. Z. Shautsukova, V. V. Bova, “Ispolzovanie modelei kollektivnogo povedeniya dlya resheniya zadach raspredelennogo iskusstvennogo intellekta”, Izvestiya Kabardino-Balkarskogo nauchnogo tsentra RAN, 2013, no. 4, 14–20

[3] V. V. Bova, A. U. Zammoev, A. N. Dukkardt, “Evolyutsionnaya model intellektualnogo analiza raznorodnykh znanii”, Izvestiya Kabardino-Balkarskogo nauchnogo tsentra RAN, 2013, no. 4, 7–13

[4] Yu. A. Kravchenko, V. V. Markov, “Prinyatie reshenii v integrirovannykh informatsionnykh modelyakh na osnove metoda analiza ierarkhii”, Izvestiya YuFU. Tekhnicheskie nauki, 2012, no. 11 (136), 212–216, Izd-vo TTI YuFU., Taganrog:

[5] V. P. Karelin, V. I. Protasov, “Primenenie metoda geneticheskogo konsiliuma dlya resheniya mnogokriterialnykh zadach diskretnoi optimizatsii v sistemakh organizatsionnogo upravleniya i prinyatiya reshenii”, Vestnik TIUiE, 2005, no. 2 (2)

[6] V. V. Bova, A. N. Dukkardt, “Primenenie iskusstvennykh neironnykh setei dlya kollektivnogo resheniya intellektualnykh zadach”, Izvestiya YuFU. Tekhnicheskie nauki, 2012, no. 7, 131–138

[7] V. Ch. Kudaev, Z. V. Nagoev, O. V. Nagoeva, “Rekursivnye agenty dlya zadach modelirovaniya intellektualnogo prinyatiya reshenii na osnove samoorganizatsii multiagentnykh kognitivnykh arkhitektur”, Izvestiya Kabardino-Balkarskogo nauchnogo tsentra RAN, 2012, no. 4 (48)

[8] V. V. Kureichik, V. M. Kureichik, S. I. Rodzin, Teoriya evolyutsionnykh vychislenii, Fizmalit., M., 2012

[9] V. M. Kureichik, V. V. Kureichik, S. I. Rodzin, “Modeli parallelizma evolyutsionnykh vychislenii”, Vestnik RGUPS, 2011, no. 3, 93–97

[10] Yu. Yu. Voevodin, L. G. Komartsova, “Primenenie geneticheskogo algoritma dlya optimizatsii parametrov neironnoi seti v zadachakh klassifikatsii”, Informatika: problemy, metodologiya, tekhnologii, 2005, 42–46

[11] Y. A. Kravchenko, V. V. Kureichik, L. A. Gladkov, “Evolutionary Algorithm for Extremal Subsets Comprehension in Graphs”, World Applied Sciences Journal, 27 (2013), 1212–1217

[12] V. V. Bova, A. N. Dukkardt, “Primenenie geneticheskikh algoritmov dlya optimizatsii parametrov neirosetevoi modeli v zadachakh izvlecheniya znanii”, Informatika, vychislitelnaya tekhnika i inzhenernoe obrazovanie, 2012, no. 2 (9)