Can I read Sequential Neural Models with Stochastic Layers on EtoBox?

Sequential Neural Models with Stochastic Layers by Fraccaro, Marco; Sønderby, Søren Kaae; Paquet, Ulrich; Winther, Ole is a scholarly article available to read on EtoBox.

What is Sequential Neural Models with Stochastic Layers about?

How can we efficiently propagate uncertainty in a latent state representation with recurrent neural networks? This paper introduces stochastic recurrent neural networks which glue a deterministic recurrent neural network and a state space model together to form a stochastic and sequential neural generative model. The clear separation of deterministic and stochastic layers allows a structured variational inference network to track the factorization of the model's posterior distribution. By retaining both the nonlinear recursive structure of a recurrent neural network and averaging over the uncertainty in a latent path, like a state space model, we improve the state of the art results on the Blizzard and TIMIT speech modeling data sets by a large margin, while achieving comparable performances to competing methods on polyphonic music modeling.

Author

Fraccaro, Marco; Sønderby, Søren Kaae; Paquet, Ulrich; Winther, Ole

Published

2016

Language

EN