AdamB: Decoupled Bayes by Backprop With Gaussian Scale Mixture Prior

AdamB: Decoupled Bayes by Backprop With Gaussian Scale Mixture Prior

Overfitting of neural networks to training data is one of the most significant problems in machine learning. Bayesian neural networks (BNNs) are known to be robust against overfitting owing to their ability to model parameter uncertainty. Bayes by Backprop (BBB), a simple variational inference appro...

Full description

Bibliographic Details
Main Authors: Keigo Nishida, Makoto Taiji
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Bayesian neural networks
covariate shift
decoupled weight decay
deep neural networks
uncertainty
variational inference
Online Access:https://ieeexplore.ieee.org/document/9874837/

Internet

https://ieeexplore.ieee.org/document/9874837/

Similar Items