Dropout inference in Bayesian neural networks with alpha-divergences
To obtain uncertainty estimates with real-world Bayesian deep learning models, practical inference approximations are needed. Dropout variational inference (VI) for example has been used for machine vision and medical applications, but VI can severely underestimates model uncertainty. Alpha-divergen...
| Main Authors: | , |
|---|---|
| Format: | Conference item |
| Published: |
PMLR
2017
|