Prediction Under Uncertainty with Error-Encoding Networks
arXiv:1711.04994
Abstract
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 components 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 a forward model. Our method uses a supervised 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 consistently generate diverse predictions without the need for alternating minimization over a latent space or adversarial training.
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Improved Techniques for Training GANs
- Decomposing Motion and Content for Natural Video Sequence Prediction
- Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning
- Unrolled Generative Adversarial Networks
- Unsupervised Learning for Physical Interaction through Video Prediction
- Optimizing the Latent Space of Generative Networks
- Deep Predictive Coding Networks
Cited by in corpus (7)
- A Review on Deep Learning Techniques for Video Prediction
- Variational Inference for Data-Efficient Model Learning in POMDPs
- Neural Learning of One-of-Many Solutions for Combinatorial Problems in Structured Output Spaces
- LMVP: Video Predictor with Leaked Motion Information
- PHYRE: A New Benchmark for Physical Reasoning
- Graph Deep Factors for Forecasting
- Stochastic Dynamics for Video Infilling