AdamB: Decoupled Bayes by Backprop With Gaussian Scale Mixture Prior
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Access"
DOI: 10.1109/access.2022.3203484
Abstract: 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… read more here.
Keywords: bayes backprop; decoupled bayes; adamb; gaussian scale ... See more keywords