Preskoči na sadržaj
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...

Cijeli opis

Spremljeno u:
Bibliografski detalji
Glavni autori: 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
Jezik:English
Izdano: Institute of Electrical and Electronics Engineers Inc. 2024
Teme:
Caputo
Stochastic gradient descent
Convolutional neural networks
Fractional derivatives of Riemann-Liouville
Grunwald-Letnikov
Multilayer perceptron
Optimization algorithms
Online pristup:https://dspace.ncfu.ru/handle/123456789/29336
Oznake: Dodaj oznaku
Bez oznaka, Budi prvi tko označuje ovaj zapis!

Internet

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

Similar Items