Implementation of Caputo type fractional derivative chain rule on back propagation algorithm

Fractional gradient computation is a challenging task for neural networks. In this study, the brief history of fractional derivation is abstracted, and the core framework of the Faà di Bruno formula is implemented to the fractional gradient computation problem. As an analytical approach to solve the...

Celý popis

Podrobná bibliografia

Vydané v:	Applied soft computing Ročník 155; s. 111475
Hlavní autori:	Candan, Mücahid, Çubukçu, Mete
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Elsevier B.V 01.04.2024
Predmet:	Back propagation Caputo derivative Cross validation Fractional gradient Fractional neural network Regularization Back propagation Cross validation Fractional neural network Regularization Caputo derivative Fractional gradient
ISSN:	1568-4946, 1872-9681
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!