Timezone: »

 
Poster
DISCO Nets : DISsimilarity COefficients Networks
Diane Bouchacourt · Pawan K Mudigonda · Sebastian Nowozin

Mon Dec 05 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #11
in Monday Posters »

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.

Keywords: Deep Learning or Neural Networks

Author Information

Diane Bouchacourt (University of Oxford)
Pawan K Mudigonda (University of Oxford)
Sebastian Nowozin (DeepMind)

More from the Same Authors