Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness.

Andrey Malinin Mark J. F. Gales

Published in: CoRR (2019)

Keyphrases

kl divergence
kullback leibler
kullback leibler divergence
gaussian mixture
information theoretic
mahalanobis distance
gaussian distribution
prior knowledge
information theory
translation model
training set
prior information
co occurrence
language model
posterior distribution
exponential family