Přeskočit na obsah
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...

Celý popis

Uloženo v:
Podrobná bibliografie
Hlavní autoři: Abdulkadirov, R. I., Абдулкадиров, Р. И., Lyakhov, P. A., Ляхов, П. А., Baboshina, V. A., Бабошина, В. А., Nagornov, N. N., Нагорнов, Н. Н.
Médium: Статья
Jazyk:English
Vydáno: Institute of Electrical and Electronics Engineers Inc. 2024
Témata:
Caputo
Stochastic gradient descent
Convolutional neural networks
Fractional derivatives of Riemann-Liouville
Grunwald-Letnikov
Multilayer perceptron
Optimization algorithms
On-line přístup:https://dspace.ncfu.ru/handle/123456789/29336
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo otaguje tento záznam!

Internet

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

Podobné jednotky