Frequentist uncertainty estimates for deep learning

11/02/2018
by   Natasa Tagasovska, et al.
0

We provide frequentist estimates of aleatoric and epistemic uncertainty for deep neural networks. To estimate aleatoric uncertainty we propose simultaneous quantile regression, a loss function to learn all the conditional quantiles of a given target variable. These quantiles lead to well-calibrated prediction intervals. To estimate epistemic uncertainty we propose training certificates, a collection of diverse non-trivial functions that map all training samples to zero. These certificates map out-of-distribution examples to non-zero values, signaling high epistemic uncertainty. We compare our proposals to prior art in various experiments.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset