We introduce GAUDI, a generative model capable of capturing the distribu...
Thanks to the tractability of their likelihood, some deep generative mod...
In this work, we propose a new family of generative flows on an augmente...
While normalizing flows have led to significant advances in modeling
hig...
Flow based models such as Real NVP are an extremely powerful approach to...
Generative models that can model and predict sequences of future events ...
We consider the setting of an agent with a fixed body interacting with a...
In this paper, we study two aspects of the variational autoencoder (VAE)...
Despite their overwhelming capacity to overfit, deep learning architectu...
Unsupervised learning of probabilistic models is a central yet challengi...
Theano is a Python library that allows to define, optimize, and evaluate...
Stochastic binary hidden units in a multi-layer perceptron (MLP) network...
We demonstrate that there is significant redundancy in the parameterizat...