Hoppa till innehåll
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...

Full beskrivning

Sparad:
Bibliografiska uppgifter
Huvudupphovsmän: Abdulkadirov, R. I., Абдулкадиров, Р. И., Lyakhov, P. A., Ляхов, П. А., Baboshina, V. A., Бабошина, В. А., Nagornov, N. N., Нагорнов, Н. Н.
Materialtyp: Статья
Språk:English
Publicerad: Institute of Electrical and Electronics Engineers Inc. 2024
Ämnen:
Caputo
Stochastic gradient descent
Convolutional neural networks
Fractional derivatives of Riemann-Liouville
Grunwald-Letnikov
Multilayer perceptron
Optimization algorithms
Länkar:https://dspace.ncfu.ru/handle/123456789/29336
Taggar: Lägg till en tagg
Inga taggar, Lägg till första taggen!

Internet

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

Liknande verk