M. Pawan Kumar
 
 

HOME

RESEARCH

PUBLICATIONS

GROUP

TALKS

TEACHING

CV

 

 

 

 

 

 

DISCO NETS: DISSIMILARITY COEFFICIENT NETWORKS

D. Bouchacourt, M. Pawan Kumar and S. Nowozin

In Proceedings of Advances in Neural Information Processing Systems (NIPS), 2016

We present a new type of probabilistic model which we call DISsimilarity COefficient Networks (DISCO Nets). DISCO Nets allow us to efficiently sample from a posterior distribution parametrised by a neural network. During training, DISCO Nets are learned by minimising the dissimilarity coefficient between the true distribution and the estimated distribution. This allows us to tailor the training to the loss related to the task at hand. We empirically show that (i) by modeling uncertainty on the output value, DISCO Nets outperform equivalent non-probabilistic predictive networks and (ii) DISCO Nets accurately model the uncertainty of the output, outperforming existing probabilistic models based on deep neural networks.

[Paper]    [Supplementary Material]    [Project Webpage]