Learning to Linearize Under Uncertainty

Part of Advances in Neural Information Processing Systems 28 (NIPS 2015)

Bibtex »Metadata »Paper »Reviews »

Authors

Ross Goroshin, Michael F. Mathieu, Yann LeCun

Abstract

Training deep feature hierarchies to solve supervised learning tasks has achieving state of the art performance on many problems in computer vision. However, a principled way in which to train such hierarchies in the unsupervised setting has remained elusive. In this work we suggest a new architecture and loss for training deep feature hierarchies that linearize the transformations observed in unlabelednatural video sequences. This is done by training a generative model to predict video frames. We also address the problem of inherent uncertainty in prediction by introducing a latent variables that are non-deterministic functions of the input into the network architecture.