Prediction Under Uncertainty with Error Encoding Networks

ICLR 2018  ·  Mikael Henaff, Junbo Zhao, Yann Lecun ·

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 which is fed into the forward model. Our method uses a simple su- pervised training objective which is fast and easy to train. We evaluate it in the context of video prediction on multiple datasets and show that it is able to consi- tently generate diverse predictions without the need for alternating minimization over a latent space or adversarial training.

PDF Abstract
No code implementations yet. Submit your code now


  Add Datasets introduced or used in this paper

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.


No methods listed for this paper. Add relevant methods here