{"id":15398,"date":"2023-01-13T09:41:57","date_gmt":"2023-01-13T07:41:57","guid":{"rendered":"http:\/\/journals.khnu.km.ua\/vestnik\/?p=15398"},"modified":"2023-02-15T00:55:26","modified_gmt":"2023-02-14T22:55:26","slug":"nejroevolyuczijni-algorytmy-dlya-generuvannya-nejronnyh-merezh","status":"publish","type":"post","link":"https:\/\/journals.khnu.km.ua\/vestnik\/?p=15398","title":{"rendered":"\u041d\u0435\u0439\u0440\u043e\u0435\u0432\u043e\u043b\u044e\u0446\u0456\u0439\u043d\u0456 \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c\u0438 \u0434\u043b\u044f \u0433\u0435\u043d\u0435\u0440\u0443\u0432\u0430\u043d\u043d\u044f \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u0438\u0445 \u043c\u0435\u0440\u0435\u0436"},"content":{"rendered":"

<\/p>\n

\u041d\u0415\u0419\u0420\u041e\u0415\u0412\u041e\u041b\u042e\u0426\u0406\u0419\u041d\u0406 \u0410\u041b\u0413\u041e\u0420\u0418\u0422\u041c\u0418 \u0414\u041b\u042f \u0413\u0415\u041d\u0415\u0420\u0423\u0412\u0410\u041d\u041d\u042f \u041d\u0415\u0419\u0420\u041e\u041d\u041d\u0418\u0425 \u041c\u0415\u0420\u0415\u0416<\/p>\n

NEUROEVOLUTIONARY ALGORITHMS FOR NEURAL NETWORKS GENERATING<\/p>\n

\u0421\u0442\u043e\u0440\u0456\u043d\u043a\u0438: 239-244. \u041d\u043e\u043c\u0435\u0440: \u21166, 2022 (315)\u00a0<\/strong> \"\"<\/a>
\n\u0410\u0432\u0442\u043e\u0440\u0438:<\/strong>
\n\u0422\u0418\u041c\u041e\u0428\u0415\u041d\u041a\u041e \u041f\u0430\u0432\u043b\u043e
\n\u041d\u0430\u0446\u0456\u043e\u043d\u0430\u043b\u044c\u043d\u0438\u0439 \u0443\u043d\u0456\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442 \u00ab\u041b\u044c\u0432\u0456\u0432\u0441\u044c\u043a\u0430 \u043f\u043e\u043b\u0456\u0442\u0435\u0445\u043d\u0456\u043a\u0430\u00bb
\nORCID ID: 0000-0002-5510-1963<\/a>
\npavlo.tymoshenko.knm.2018@lpnu.ua
\n\u0417\u0410\u0421\u041e\u0411\u0410 \u0404\u0432\u0433\u0435\u043d
\n\u041d\u0430\u0446\u0456\u043e\u043d\u0430\u043b\u044c\u043d\u0438\u0439 \u0443\u043d\u0456\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442 \u00ab\u041b\u044c\u0432\u0456\u0432\u0441\u044c\u043a\u0430 \u043f\u043e\u043b\u0456\u0442\u0435\u0445\u043d\u0456\u043a\u0430\u00bb
\nORCID ID: 0000-0003-4830-8306<\/a>
\ngeka.zasoba@gmail.com
\n\u041a\u041e\u0412\u0410\u041b\u042c\u0427\u0423\u041a \u041e\u043b\u0435\u043a\u0441\u0430\u043d\u0434\u0440
\n\u041d\u0430\u0446\u0456\u043e\u043d\u0430\u043b\u044c\u043d\u0438\u0439 \u0443\u043d\u0456\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442 \u00ab\u041b\u044c\u0432\u0456\u0432\u0441\u044c\u043a\u0430 \u043f\u043e\u043b\u0456\u0442\u0435\u0445\u043d\u0456\u043a\u0430\u00bb
\nORCID ID: \u00a00000-0002-0148-0320<\/a>
\noleksandr.v.kovalchuk@lpnu.ua
\n\u041f\u0428\u0415\u041d\u0418\u0427\u041d\u0418\u0419 \u041e\u043b\u0435\u043a\u0441\u0430\u043d\u0434\u0440
\n\u041d\u0430\u0446\u0456\u043e\u043d\u0430\u043b\u044c\u043d\u0438\u0439 \u0443\u043d\u0456\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442 \u00ab\u041b\u044c\u0432\u0456\u0432\u0441\u044c\u043a\u0430 \u043f\u043e\u043b\u0456\u0442\u0435\u0445\u043d\u0456\u043a\u0430\u00bb
\nORCID ID: 0000-0001-8823-7472<\/a>
\noleksandr.y.pshenychnyi@lpnu.ua
\nTYMOSHENKO Pavlo, ZASOBA Yevgen, KOVALCHUK Olexander, PSHENYCHNYY Olexander
\nLviv Polytechnic National University
\nDOI:<\/strong> https:\/\/www.doi.org\/10.31891\/2307-5732-2022-315-6-240-244<\/a><\/p>\n

\u0410\u043d\u043e\u0442\u0430\u0446\u0456\u044f \u043c\u043e\u0432\u043e\u044e \u043e\u0440\u0438\u0433\u0456\u043d\u0430\u043b\u0443<\/strong><\/p>\n

\u0412\u0438\u0440\u0456\u0448\u0435\u043d\u043d\u044f \u0456\u043d\u0436\u0435\u043d\u0435\u0440\u043d\u0438\u0445 \u0437\u0430\u0434\u0430\u0447 \u0437\u0430 \u0434\u043e\u043f\u043e\u043c\u043e\u0433\u043e\u044e \u0437\u0432\u0438\u0447\u0430\u0439\u043d\u0438\u0445 \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u0438\u0445 \u043c\u0435\u0440\u0435\u0436 \u0432\u0438\u043c\u0430\u0433\u0430\u044e\u0442\u044c \u0442\u0440\u0438\u0432\u0430\u043b\u0438\u0445 \u0434\u043e\u0441\u043b\u0456\u0434\u0436\u0435\u043d\u044c \u0449\u043e\u0434\u043e \u0432\u0438\u0431\u043e\u0440\u0443 \u0430\u0440\u0445\u0456\u0442\u0435\u043a\u0442\u0443\u0440\u0438 \u0442\u0430 \u0433\u0456\u043f\u0435\u0440\u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u0456\u0432. \u0421\u0438\u043b\u044c\u043d\u0438\u0439 \u0448\u0442\u0443\u0447\u043d\u0438\u0439 \u0456\u043d\u0442\u0435\u043b\u0435\u043a\u0442 \u0431\u0443\u0432 \u0431\u0438 \u043f\u043e\u0437\u0431\u0430\u0432\u043b\u0435\u043d\u0438\u043c \u0442\u0430\u043a\u0438\u0445 \u043d\u0435\u0434\u043e\u043b\u0456\u043a\u0456\u0432. \u041f\u043e\u0434\u0456\u0431\u043d\u0456 \u0434\u043e\u0441\u043b\u0456\u0434\u0436\u0435\u043d\u043d\u044f \u043f\u0440\u043e\u0432\u043e\u0434\u044f\u0442\u044c\u0441\u044f \u0437 \u0432\u0438\u043a\u043e\u0440\u0438\u0441\u0442\u0430\u043d\u043d\u044f\u043c \u0434\u0443\u0436\u0435 \u0448\u0438\u0440\u043e\u043a\u043e\u0433\u043e \u0441\u043f\u0435\u043a\u0442\u0440\u0443 \u043f\u0456\u0434\u0445\u043e\u0434\u0456\u0432: \u043d\u0430\u043f\u0440\u0438\u043a\u043b\u0430\u0434, \u0431\u0456\u043e\u043b\u043e\u0433\u0456\u0447\u043d\u043e\u0433\u043e (\u0441\u043f\u0440\u043e\u0431\u0438 \u0432\u0438\u0440\u043e\u0441\u0442\u0438\u0442\u0438 \u043c\u043e\u0437\u043e\u043a \u0443 \u043b\u0430\u0431\u043e\u0440\u0430\u0442\u043e\u0440\u043d\u0438\u0445 \u0443\u043c\u043e\u0432\u0430\u0445), \u0430\u043f\u0430\u0440\u0430\u0442\u043d\u043e\u0433\u043e (\u0441\u0442\u0432\u043e\u0440\u0435\u043d\u043d\u044f \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u0438\u0445 \u043f\u0440\u043e\u0446\u0435\u0441\u043e\u0440\u0456\u0432) \u0430\u0431\u043e \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043d\u043e\u0433\u043e (\u0437 \u0432\u0438\u043a\u043e\u0440\u0438\u0441\u0442\u0430\u043d\u043d\u044f\u043c \u043f\u043e\u0442\u0443\u0436\u043d\u043e\u0441\u0442\u0435\u0439 \u0437\u0432\u0438\u0447\u0430\u0439\u043d\u043e\u0433\u043e CPU \u0442\u0430 GPU). \u041c\u0435\u0442\u043e\u044e \u0440\u043e\u0431\u043e\u0442\u0438 \u0454 \u0440\u043e\u0437\u0440\u043e\u0431\u043b\u0435\u043d\u043d\u044f \u0442\u0430\u043a\u043e\u0457 \u0441\u0438\u0441\u0442\u0435\u043c\u0438, \u044f\u043a\u0430 \u0434\u043e\u0437\u0432\u043e\u043b\u044f\u043b\u0430 \u0431\u0438 \u0437\u0430 \u0434\u043e\u043f\u043e\u043c\u043e\u0433\u043e\u044e \u0435\u0432\u043e\u043b\u044e\u0446\u0456\u0439\u043d\u0438\u0445 \u043f\u0456\u0434\u0445\u043e\u0434\u0456\u0432 \u0433\u0435\u043d\u0435\u0440\u0443\u0432\u0430\u0442\u0438 \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u0456 \u043c\u0435\u0440\u0435\u0436\u0456, \u043f\u0440\u0438\u0434\u0430\u0442\u043d\u0456 \u0434\u043b\u044f \u0440\u043e\u0437\u0432\u2019\u044f\u0437\u0443\u0432\u0430\u043d\u043d\u044f \u0437\u0430\u0434\u0430\u0447. \u041f\u043e\u0434\u0456\u0431\u043d\u0438\u0439 \u043d\u043e\u0441\u0438\u0442\u044c \u043d\u0430\u0437\u0432\u0443 \u00ab\u043d\u0435\u0439\u0440\u043e\u0435\u0432\u043e\u043b\u044e\u0446\u0456\u0457\u00bb. \u0414\u043e \u043c\u0435\u0442\u0438 \u0446\u0456\u0454\u0457 \u0440\u043e\u0431\u043e\u0442\u0438 \u0442\u0430\u043a\u043e\u0436 \u0432\u0445\u043e\u0434\u0438\u0442\u044c \u0434\u043e\u0441\u043b\u0456\u0434\u0436\u0435\u043d\u043d\u044f \u043e\u0441\u043e\u0431\u043b\u0438\u0432\u043e\u0441\u0442\u0435\u0439 \u043c\u043e\u0436\u043b\u0438\u0432\u0438\u0445 \u0437\u0430\u0441\u0442\u043e\u0441\u043e\u0432\u043d\u0438\u0445 \u0435\u0432\u043e\u043b\u044e\u0446\u0456\u0439\u043d\u0438\u0445 \u0441\u0442\u0440\u0430\u0442\u0435\u0433\u0456\u0439.
\n\u041a\u043b\u044e\u0447\u043e\u0432\u0456 \u0441\u043b\u043e\u0432\u0430: <\/strong>\u043d\u0435\u0439\u0440\u043e\u0435\u0432\u043e\u043b\u044e\u0446\u0456\u0439\u043d\u0438\u0439 \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c, \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u0430 \u043c\u0435\u0440\u0435\u0436\u0430, \u043c\u043e\u0434\u0435\u043b\u044c \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043d\u0430\u0432\u0447\u0430\u043d\u043d\u044f, \u043f\u0440\u0435\u043f\u0440\u043e\u0446\u0435\u0441\u0438\u043d\u0433 \u0434\u0430\u043d\u0438\u0445.<\/p>\n

\u0420\u043e\u0437\u0448\u0438\u0440\u0435\u043d\u0430 \u0430\u043d\u043e\u0442\u0430\u0446\u0456\u044f \u0430\u043d\u0433\u043b\u0456\u0439\u0441\u044c\u043a\u043e\u044e \u00a0\u043c\u043e\u0432\u043e\u044e<\/strong><\/p>\n

Solving engineering problems using conventional neural networks requires long-term research on the choice of architecture and hyperparameters. A strong artificial intelligence would be devoid of such shortcomings. Such research is carried out using a very wide range of approaches: for example, biological (attempts to grow a brain in laboratory conditions), hardware (creating neural processors) or software (using the power of ordinary CPUs and GPUs). The goal of the work is to develop such a system that would allow using evolutionary approaches to generate neural networks suitable for solving problems. This is called “neuroevolution”. The purpose of this work also includes the study of the features of possible applicable evolutionary strategies.
\nThe object of research in this work is a neuroevolutionary approach to solving problems of machine learning.\u00a0 The subject of research is evolutionary strategies, neural coding methods networks in the organism’s genome. The scientific novelty of the work lies in the testing of previously unused evolutionary strategies and the generalization of the obtained system to the systems of “general artificial intelligence”. A system for simulating neuroevolution was created. The specifics of implementation were considered, the choice of algorithms was justified, and their work was explained. In order to perform experiments, datasets were created and methods of applying neuroevolutionary systems were developed. It was possible to choose the most optimal training parameters, to find out the relationship between them, as well as the accuracy and speed of training. It cannot be said that the models implemented within this work directly bring us closer to strong AI. They still lack their own memory as well as a certain level of complexity. For successful use, it is necessary to configure the view of the input data or perform some calculations outside the model. However, in the future, such a system can be developed, for example, to work with SNNs, or for use on special equipment
\nKeywords:<\/strong> neuroevolutionary algorithms, artificial neural network, machine learning model, data preprocessing.<\/p>\n

\u041b\u0456\u0442\u0435\u0440\u0430\u0442\u0443\u0440\u0430<\/strong><\/p>\n

    \n
  1. Garcia A., Arbelaitz O., Linaza M.T., Vansteenwegen P., Souffriau W. (2010). Personalized Tourist Route Generation. In: Daniel F., Facca F.M. (eds) Current Trends in Web Engineering. ICWE 2010. Lecture Notes in Computer Science, vol 6385. Springer, Berlin, Heidelberg. https:\/\/doi.org\/10.1007\/978-3-642-16985-4_47<\/li>\n
  2. Ramesh Aditya Zero Shot Text to Image Generation. arXiv.org. URL: https:\/\/arxiv.org\/abs\/2102.12092 (03.06.2022).<\/li>\n
  3. Searle J. R. Is the Brain\u2019s Mind a Computer Program? Scientific American. 1990. \u0422. 262, \u2116 1. \u0421. 26\u201331. URL: https:\/\/doi.org\/10.1038\/scientificamerican0190-26 (03.06.2022).<\/li>\n
  4. Russell S. J. Artificial intelligence: A modern approach. 2 ed. Upper Saddle River, N.J : Prentice Hall, 2003. 1080 p.<\/li>\n
  5. Stubblefield W. A., George F. Luger Artificial Intelligence: Structures and Strategies for Complex Problem Solving. 3 ed. Addison Wesley Publishing Company, 1997. 868 p.<\/li>\n
  6. Russell S. J. Artificial intelligence: A modern approach. 2 ed. Upper Saddle River, N.J.: Prentice Hall, 2003. 1080 p.<\/li>\n
  7. Butz M. V. Towards Strong AI. KI K\u00fcnstliche Intelligenz. 2021. \u0422. 35, \u2116 1. P. 91\u2014101. URL: https:\/\/doi.org\/10.1007\/s13218-021-00705-x (23.05.2022).<\/li>\n
  8. Frederico A. C. Azevedo Equal numbers of neuronal and nonneuronal cells make the human brain an isometrically scaled up primate brain. The Journal of Comparative Neurology. 2009. \u0422. 513, \u2116 5. P. 532\u2014541. URL: https:\/\/doi.org\/10.1002\/cne.21974 (23.05.2022).<\/li>\n<\/ol>\n

     <\/p>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":3,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[1,74],"tags":[],"_links":{"self":[{"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/posts\/15398"}],"collection":[{"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=15398"}],"version-history":[{"count":4,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/posts\/15398\/revisions"}],"predecessor-version":[{"id":16001,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/posts\/15398\/revisions\/16001"}],"wp:attachment":[{"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=15398"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=15398"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=15398"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}