New method of training two-layer sigmoid neural networks using regularization

Описание

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

Конференция: International Workshop on Advanced Technologies in Material Science, Mechanical and Automation Engineering (MIP) - Engineering; Krasnoyarsk, RUSSIA; Krasnoyarsk, RUSSIA

Год издания: 2019

Идентификатор DOI: 10.1088/1757-899X/537/4/042055

Аннотация: We propose a complex learning algorithm for sigmoid Artificial Neural Networks (ANN). We introduce the concept of the working area of a neuron for sigmoid ANNs in the form of a band in the attribute space, its width and location associated with the center

Ссылки на полный текст

Издание

Журнал: IOP Conference Series: Materials Science and Engineering

Выпуск журнала: Vol. 537, Is. 4

Номера страниц: 42055

ISSN журнала: 17578981

Издатель: Institute of Physics Publishing

Авторы

  • Krutikov V.N. (Kemerovo State Univ, 6 Krasnaya St, Kemerovo 650000, Russia)
  • Kazakovtsev L.A. (Reshetnev Siberian State Univ Sci & Technol, 31 Krasnoyarsky Rabochy Av, Krasnoyarsk 660037, Russia; Siberian Fed Univ, 79 Svobodny Prospect, Krasnoyarsk, Russia)
  • Shkaberina G.Sh (Reshetnev Siberian State Univ Sci & Technol, 31 Krasnoyarsky Rabochy Av, Krasnoyarsk 660037, Russia)
  • Kazakovtsev V.L. (St Petersburg Natl Res Univ Informat Technol Mech, 49 Kronverksky Av, St Petersburg 197101, Russia)

Вхождение в базы данных