Damped Newton Stochastic Gradient Descent Method for Neural Networks Training

Damped Newton Stochastic Gradient Descent Method for Neural Networks Training

First-order methods such as stochastic gradient descent (SGD) have recently become popular optimization methods to train deep neural networks (DNNs) for good generalization; however, they need a long training time. Second-order methods which can lower the training time are scarcely used on account o...

Cijeli opis

Bibliografski detalji
Glavni autori: Jingcheng Zhou, Wei Wei, Ruizhi Zhang, Zhiming Zheng
Format: Članak
Jezik:English
Izdano: MDPI AG 2021-06-01
Serija:Mathematics
Teme:
stochastic gradient descent
damped Newton
convexity
Online pristup:https://www.mdpi.com/2227-7390/9/13/1533

Internet

https://www.mdpi.com/2227-7390/9/13/1533

Slični predmeti