NeurIPS 2015poster156 citations

Learning to Linearize Under Uncertainty

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.

BibTeX
@inproceedings{NIPS2015_eefc9e10,
 author = {Goroshin, Ross and Mathieu, Michael F and LeCun, Yann},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {C. Cortes and N. Lawrence and D. Lee and M. Sugiyama and R. Garnett},
 pages = {},
 publisher = {Curran Associates, Inc.},
 title = {Learning to Linearize Under Uncertainty},
 url = {https://proceedings.neurips.cc/paper_files/paper/2015/file/eefc9e10ebdc4a2333b42b2dbb8f27b6-Paper.pdf},
 volume = {28},
 year = {2015}
}
Learning to Linearize Under Uncertainty · NeurIPS 2015