Modeling Deep Temporal Dependencies with Recurrent Grammar Cells""

Part of Advances in Neural Information Processing Systems 27 (NIPS 2014)

Bibtex Metadata Paper Reviews Supplemental


Vincent Michalski, Roland Memisevic, Kishore Konda


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 network, by training it to predict future frames from the current one and the inferred transformation using backprop-through-time. We also show how stacking multiple 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.