Timezone: »

A Recurrent Latent Variable Model for Sequential Data
Junyoung Chung · Kyle Kastner · Laurent Dinh · Kratarth Goel · Aaron Courville · Yoshua Bengio

Mon Dec 07 04:00 PM -- 08:59 PM (PST) @ 210 C #21

In this paper, we explore the inclusion of latent random variables into the hidden state of a recurrent neural network (RNN) by combining the elements of the variational autoencoder. We argue that through the use of high-level latent random variables, the variational RNN (VRNN) can model the kind of variability observed in highly structured sequential data such as natural speech. We empirically evaluate the proposed model against other related sequential models on four speech datasets and one handwriting dataset. Our results show the important roles that latent random variables can play in the RNN dynamics.

Author Information

Junyoung Chung (University of Montreal)
Kyle Kastner (Universite de Montreal)
Laurent Dinh (University of Montreal)
Kratarth Goel (University of Montreal)
Aaron Courville (U. Montreal)
Yoshua Bengio (U. Montreal)

More from the Same Authors