Léim chuig an ábhar
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...

Cur síos iomlán

Sábháilte in:
Sonraí bibleagrafaíochta
Príomhchruthaitheoirí: Abdulkadirov, R. I., Абдулкадиров, Р. И., Lyakhov, P. A., Ляхов, П. А., Baboshina, V. A., Бабошина, В. А., Nagornov, N. N., Нагорнов, Н. Н.
Formáid: Статья
Teanga:English
Foilsithe / Cruthaithe: Institute of Electrical and Electronics Engineers Inc. 2024
Ábhair:
Caputo
Stochastic gradient descent
Convolutional neural networks
Fractional derivatives of Riemann-Liouville
Grunwald-Letnikov
Multilayer perceptron
Optimization algorithms
Rochtain ar líne:https://dspace.ncfu.ru/handle/123456789/29336
Clibeanna: Cuir clib leis
Níl clibeanna ann, Bí ar an gcéad duine le clib a chur leis an taifead seo!

Ar líne

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

Míreanna comhchosúla