Initial work on variational autoencoders assumed independent latent vari...
Graphical flows add further structure to normalizing flows by encoding
n...
We propose a method for combining probabilistic outputs of classifiers t...
We consider estimating the marginal likelihood in settings with independ...
Bayesian neural networks (BNNs) have developed into useful tools for
pro...
Recent work in signal propagation theory has shown that dropout limits t...
Recent work has established the equivalence between deep neural networks...
The problem of coordination without a priori information about the
envir...
The problem of coordination without a priori information about the
envir...
Stochastic regularisation is an important weapon in the arsenal of a dee...
Denoising autoencoders (DAEs) have proven useful for unsupervised
repres...