Abstract
Deep neural networks (DNNs) have excellent representative power and are state
of the art classifiers on many tasks. However, they often do not capture their
own uncertainties well making them less robust in the real world as they
overconfidently extrapolate and do not notice domain shift. Gaussian processes
(GPs) with RBF kernels on the other hand have better calibrated uncertainties
and do not overconfidently extrapolate far from data in their training set.
However, GPs have poor representational power and do not perform as well as
DNNs on complex domains. In this paper we show that GP hybrid deep networks,
GPDNNs, (GPs on top of DNNs and trained end-to-end) inherit the nice properties
of both GPs and DNNs and are much more robust to adversarial examples. When
extrapolating to adversarial examples and testing in domain shift settings,
GPDNNs frequently output high entropy class probabilities corresponding to
essentially "don't know". GPDNNs are therefore promising as deep architectures
that know when they don't know.
Users
Please
log in to take part in the discussion (add own reviews or comments).