Prediction Under Uncertainty with Error Encoding Networks
arXiv: Artificial Intelligence, 2018.
In this work we introduce a new framework for performing temporal predictions in the presence of uncertainty. It is based on a simple idea of disentangling com- ponents of the future state which are predictable from those which are inherently unpredictable, and encoding the unpredictable components into a low-dimensional latent variable w...More
PPT (Upload PPT)