DMCA
Modeling deep temporal dependencies with recurrent grammar cells (2014)
| Venue: | In Advances in Neural Information Processing Systems 27 |
| Citations: | 7 - 0 self |
BibTeX
@INPROCEEDINGS{Michalski14modelingdeep,
author = {Vincent Michalski and Roland Memisevic and Kishore Konda},
title = {Modeling deep temporal dependencies with recurrent grammar cells},
booktitle = {In Advances in Neural Information Processing Systems 27},
year = {2014},
pages = {1925--1933},
publisher = {Curran Associates, Inc}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We propose modeling time series by representing the transformations that take a frame at time t to a frame at time t+1. To this end we show how a bi-linear model of transformations, such as a gated autoencoder, can be turned into a recurrent net-work, by training it to predict future frames from the current one and the inferred transformation using backprop-through-time. We also show how stacking multi-ple layers of gating units in a recurrent pyramid makes it possible to represent the ”syntax ” of complicated time series, and that it can outperform standard recurrent neural networks in terms of prediction accuracy on a variety of tasks. 1
