资源分类
》 资源 》论文》Bayesian Uncertainty Estimation for Batch Normalized Deep Networks

Bayesian Uncertainty Estimation for Batch Normalized Deep Networks

2020-03-19 | |  49 |   36 |   0

Abstract

We show that training a deep network using batch normalization is equivalent to approximate inference in Bayesian models. We further demonstrate that this finding allows us to make meaningful estimates of the model uncertainty using conventional architectures, without modifications to the network or the training procedure. Our approach is thoroughly validated by measuring the quality of uncertainty in a series of empirical experiments on different tasks. It outperforms baselines with strong statistical significance, and displays competitive performance with recent Bayesian approaches.

上一篇：Does Distributionally Robust Supervised Learning Give Robust Classifiers

下一篇：The Mechanics of n-Player Differentiable Games

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...