A Bayesian Approach to Invariant Deep Neural Networks

07/20/2021
by   Nikolaos Mourdoukoutas, et al.
0

We propose a novel Bayesian neural network architecture that can learn invariances from data alone by inferring a posterior distribution over different weight-sharing schemes. We show that our model outperforms other non-invariant architectures, when trained on datasets that contain specific invariances. The same holds true when no data augmentation is performed.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset