Пропуск в контексте
Improving the Accuracy of Neural Network Pattern Recognition by Fractional Gradient Descent

Improving the Accuracy of Neural Network Pattern Recognition by Fractional Gradient Descent

In this paper we propose the fractional gradient descent for increasing the training and work of modern neural networks. This optimizer searches the global minimum of the loss function considering the fractional gradient directions achieved by Riemann-Liouville, Caputo, and Grunwald-Letnikov derivat...

Fuld beskrivelse

Сохранить в:
Bibliografiske detaljer
Главные авторы: Abdulkadirov, R. I., Абдулкадиров, Р. И., Lyakhov, P. A., Ляхов, П. А., Baboshina, V. A., Бабошина, В. А., Nagornov, N. N., Нагорнов, Н. Н.
Format: Статья
Sprog:English
Udgivet: Institute of Electrical and Electronics Engineers Inc. 2024
Fag:
Caputo
Stochastic gradient descent
Convolutional neural networks
Fractional derivatives of Riemann-Liouville
Grunwald-Letnikov
Multilayer perceptron
Optimization algorithms
Online adgang:https://dspace.ncfu.ru/handle/123456789/29336
Tags: Tilføj Tag
Ingen Tags, Vær først til at tagge denne postø!

Internet

https://dspace.ncfu.ru/handle/123456789/29336

Lignende værker