Using genetic algorithm with adaptive mutation mechanism for neural networks design and training

Y. R. Tsoy, V. G. Spitsyn

Результат исследований: Материалы для книги/типы отчетовМатериалы для конференции

10 Цитирования (Scopus)

Аннотация

In this paper a developed evolutionary algorithm (NEvA) for simultaneous connections and weights of neural network training is described. A distinctive feature of the algorithm is flexible and effective evolutionary search and a balanced resulting neural network structure due to adaptive mutation operator. In NEvA neural network structure changes, caused by mutation operator, as well as mutation rate are defined independently for each individual. Two different problems are chosen to test the algorithm. The first one is a simple 2-bit parity problem, well known as XOR problem, and the second is a neurocontrol problem of t and 2 poles balancing. A comparison of obtained results with results of other algorithms is presented.

Язык оригиналаАнглийский
Название основной публикацииProceedings - 9th Russian-Korean International Symposium on Science and Technology, KORUS-2005
Страницы709-714
Число страниц6
Том1
DOI
СостояниеОпубликовано - 2005
Событие9th Russian-Korean International Symposium on Science and Technology, KORUS-2005 - Novosibirsk, Российская Федерация
Продолжительность: 26 июн 20052 июл 2005

Другое

Другое9th Russian-Korean International Symposium on Science and Technology, KORUS-2005
СтранаРоссийская Федерация
ГородNovosibirsk
Период26.6.052.7.05

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Подробные сведения о темах исследования «Using genetic algorithm with adaptive mutation mechanism for neural networks design and training». Вместе они формируют уникальный семантический отпечаток (fingerprint).

Цитировать