Constructive algorithms as a method of achieving plasticity of ANNs

Тип публикации: доклад, тезисы доклада, статья из сборника материалов конференций

Конференция: International Scientific Conference on Metrological Support of Innovative Technologies, ICMSIT 2020

Год издания: 2020

Идентификатор DOI: 10.1088/1742-6596/1515/2/022085

Аннотация: Artificial neural networks are a model of natural neural networks. For natural neural networks is characterized by incessant genesis, which causes their plasticity and stability. In a changing environment, artificial neural networks must provide not only stability, but also plasticity. The solution to the problem is constructive algorithms that allow you to create architectures with an optimal structure. © Published under licence by IOP Publishing Ltd.

Ссылки на полный текст

Издание

Журнал: Journal of Physics: Conference Series

Выпуск журнала: Vol. 1515, Is. 2

ISSN журнала: 17426588

Издатель: Institute of Physics Publishing22085

Персоны

Kovalev I.V. (Siberian Federal University, Svobodny Ave. 79, Krasnoyarsk, 660041, Russian Federation)
Yakasova N.V. (Siberian Federal University, Svobodny Ave. 79, Krasnoyarsk, 660041, Russian Federation, Khakassia State University Named after N. F. Katanov, Lenin Ave.90, Abakan, 655017, Russian Federation)

Вхождение в базы данных

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