Distributed self-configuring evolutionary algorithms for artificial neural networks design
Автор: Khritonenko Dmitriy Ivanovich, Semenkin Evgeny Stanislavovich
Журнал: Сибирский аэрокосмический журнал @vestnik-sibsau
Рубрика: 2-я международная конференция по математическим моделям и их применению
Статья в выпуске: 4 (50), 2013 года.
Бесплатный доступ
In this paper we describe the method of automatic neural network design based on the modified evolutionary algorithms. The main features of the modification proposed are self-configuration and the usage of distributed computing. Implemented algorithms have been tested on the set of classification tasks. The comparison of the genetic algorithm and the genetic programming algorithm’s efficiencies is presented.
Genetic algorithm, genetic programming, self-configuration, distributed computing, artificial neural network, classifiers, automated design
Короткий адрес: https://sciup.org/148177127
IDR: 148177127
