APPLICATION OF ARTIFICIAL NEURAL NETWORKS IN THE PROBLEMS OF MANAGING A GENETIC ALGORITHM

In modern intelligent decision support systems, there is still a problem associated with improving performance in structural and parametric synthesis of large discrete systems with specified behavior based on genetic algorithms. Currently, there are two main areas of research that are designed for mathematical or hardware-based performance improvements. One of the ways to increase hardware performance is to use parallel computing, which includes GPGPU (General-purpose computing on graphics processing units) technology. In this paper, we consider the possibility of increasing the speed of intelligent systems using a mathematical tool of artificial neural networks by introducing a control module for the genetic algorithm directly when performing decision synthesis. The process of structuralparametric synthesis is controlled by predicting and assessing the state of the genetic algorithm (convergence, attenuation, finding the population at local extremes) using artificial neural networks. This allows you to change the parameters of the operators directly in the process of decision synthesis, changing their destructive ability relative to the binary string, which leads to a change in the trajectory of the population in the decision space, and as a result, should increase the speed of intelligent decision support systems.

1. Orlov, A.N. Kombinirovannyj geneticheskij algoritm resheniya zadachi raskroya / A.N. Orlov, V.V. Kurejchik, A.E. Glushchenko. 2016;6(179):5-13.

2. Petrosov D.A. Matematicheskaya model' formirovaniya konfiguracii vychislitel'noj tekhniki na osnove triggerov. Vestnik Izhevskogo gosudarstvennogo tekhnicheskogo universiteta. 2009;3:139-143.

3. Manzhula V.G., Fedyashov D.S. Nejronnye seti Kohonena i nechetkie nejronnye seti v intellektual'nom analize dannyh. Fundamental'nye issledovaniya. 2011;4:108-114.

4. Hajkin S. Nejronnye seti polnyj kurs, 2-e izdanie: Per. s angl. M.: Izdatel'skij dom «Vil'yams». 2006:1104.

5. Stepovoj A.A., Rubanov V.G. Povyshenie zhivuchesti mobil'nogo robota s ispol'zovaniem apparata nejronnyh setej. Matematicheskie metody v tekhnike i tekhnologiyah: sb. tr. mezhdunar. nauch. konf.: v 12 t. pod obshch. red. A. A. Bol'shakova. SPb.: Izd-vo Politekhn. un-ta. 2019;3:26-29.

6. Petrosov D.A., Ignatenko V.A. Primenenie informacionnyh setej Petri dlya modelirovaniya nejronnoj seti v zadache upravleniya adaptirovannym geneticheskim algoritmom pri reshenii zadach strukturno-parametricheskogo sinteza diskretnyh system. Uspekhi sovremennoj nauki i obrazovaniya. 2016;5(12):138-141.