Learning to Linearize Under Uncertainty

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.

Cite

Text

Goroshin et al. "Learning to Linearize Under Uncertainty." Neural Information Processing Systems, 2015.

Markdown

[Goroshin et al. "Learning to Linearize Under Uncertainty." Neural Information Processing Systems, 2015.](https://mlanthology.org/neurips/2015/goroshin2015neurips-learning/)

BibTeX

@inproceedings{goroshin2015neurips-learning,
  title     = {{Learning to Linearize Under Uncertainty}},
  author    = {Goroshin, Ross and Mathieu, Michael F and LeCun, Yann},
  booktitle = {Neural Information Processing Systems},
  year      = {2015},
  pages     = {1234-1242},
  url       = {https://mlanthology.org/neurips/2015/goroshin2015neurips-learning/}
}