Adaptive Weight Decay for Deep Neural Networks

Adaptive Weight Decay for Deep Neural Networks

Regularization in the optimization of deep neural networks is often critical to avoid undesirable over-fitting leading to better generalization of model. One of the most popular regularization algorithms is to impose L<sub>2</sub> penalty on the model parameters resulting in the decay of...

Full description

Bibliographic Details
Main Authors: Kensuke Nakamura, Byung-Woo Hong
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Adaptive regularization
deep learning
neural networks
stochastic gradient descent
weight-decay
Online Access:https://ieeexplore.ieee.org/document/8811458/

Internet

https://ieeexplore.ieee.org/document/8811458/

Similar Items