← Search

Akihiro Matsukawa

2 accepted papers

2019

Do Deep Generative Models Know What They Don't Know?

ICLR 2019poster

A neural network deployed in the wild may be asked to make predictions for inputs that were drawn from a different distribution than that of the training data. A plethora of work has demonstrated that it is easy to find or synthesize inputs for which a neural network is highly confident yet wrong.…

Cited by 903SourcePDFScholar
2019

Hybrid Models with Deep and Invertible Features

ICML 2019oral

We propose a neural hybrid model consisting of a linear model defined on a set of features computed by a deep, invertible transformation (i.e. a normalizing flow). An attractive property of our model is that both p(features), the density of the features, and p(targets|features), the predictive distr…

Cited by 110SourcePDFScholar