The parallel genetic algorithm for construction of technological objects neural network models

Год издания: 2017

Идентификатор DOI: 10.1109/ICIEAM.2016.7911573

Ключевые слова: genetic algorithm, modelling, neural networks, optimization, parallelization, Genetic algorithms, Global optimization, Manufacture, Models, Neural networks, Computing performance, Global optimization algorithm, Neural networks model, Neural networks structure, Parallel genetic algorithms, Parallelization techniques, Parallelizations, Parametric synthesis, Optimization

Аннотация: The parallel genetic algorithms implementation for neural networks models construction is discussed. The modification of this global optimization algorithm is proposed. The artificial neural networks are effective instrument to solve most problems of technological objectives and processes modelling. The article describes the aspects of genetic algorithms implementation for neural networks structure-parametric synthesis. It is offered to use different parallelization technique of genetic algorithm to increase computing performance. It is proposed to modify the standard multipopular parallel genetic algorithm adding its base topology dynamic adaptation. This approach enables an effective algorithm with a minimal computational difficulty. The algorithm modification shows best results, when implemented in computer network. © 2016 IEEE.

Ссылки на полный текст

Издание

Журнал: 2016 2nd International Conference on Industrial Engineering, Applications and Manufacturing, ICIEAM 2016 - Proceedings

Авторы

  • Tynchenko V.S. (Dept. of Production Machinery and Equipment for Petroleum and Natural Gas Engineering, Siberian Federal University, Krasnoyarsk, Russian Federation)
  • Petrovsky E.A. (Dept. of Production Machinery and Equipment for Petroleum and Natural Gas Engineering, Siberian Federal University, Krasnoyarsk, Russian Federation)
  • Tynchenko V.V. (Dept. of Informatics, Siberian Federal University, Krasnoyarsk, Russian Federation)

Вхождение в базы данных

Информация о публикациях загружается с сайта службы поддержки публикационной активности СФУ. Сообщите, если заметили неточности.

Вы можете отметить интересные фрагменты текста, которые будут доступны по уникальной ссылке в адресной строке браузера.