|
News of the Kabardin-Balkar scientific center of RAS, 2015, Issue 5, Pages 24–30
(Mi izkab294)
|
|
|
|
This article is cited in 2 scientific papers (total in 2 papers)
INFORMATICS
Evolutionary approach to creating a neural network
model of collective decisions of intellectual tasks
M. I. Anchekova, V. V. Bovab, O. V. Nagoevaa, A. A. Novikovb, I. A. Pshenokovaa a Institute of Computer Science and Problems of Regional Management of KBSC of the Russian Academy of Sciences,
360000, KBR, Nalchik, 37-a, I. Armand street
b Southern Federal University
344006, Rostov-on-Don, 105/42, Bolshaya Sadovaya street
Abstract:
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.
Received: 28.08.2015
Citation:
M. I. Anchekov, V. V. Bova, O. V. Nagoeva, A. A. Novikov, I. A. Pshenokova, “Evolutionary approach to creating a neural network
model of collective decisions of intellectual tasks”, News of the Kabardin-Balkar scientific center of RAS, 2015, no. 5, 24–30
Linking options:
https://www.mathnet.ru/eng/izkab294 https://www.mathnet.ru/eng/izkab/y2015/i5/p24
|
Statistics & downloads: |
Abstract page: | 69 | Full-text PDF : | 60 | References: | 12 |
|