Variational Inference in Neural Networks using an Approximate Closed-Form Objective

By Wolfgang Roth, Franz Pernkopf. 2016

14 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Jochen Gast
2. Stefan Roth
3. Kai Zhang
4. Luc Van Gool
5. Deqing Sun
6. Wangmeng Zuo
7. Fredrik K. Gustafsson
8. Bernt Schiele

Citations in the corpus

• Lightweight Probabilistic Deep Networks (2018, methodology): “…different training paradigms: (SM mean + XE) We directly feed the mean-prediction into a softmax as suggested by [27] and use the cross-entropy loss; (SM approx + XE) we apply the second-order softmax approximation of [44] with a cross-entropy loss; (Dir + CLLH) our Dirichlet output layer from Sec.”