Skip to yearly menu bar Skip to main content


Sequential Neural Models with Stochastic Layers

Marco Fraccaro · Søren Kaae Sønderby · Ulrich Paquet · Ole Winther

Area 5+6+7+8 #179

Keywords: [ Variational Inference ] [ Deep Learning or Neural Networks ]


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.

Live content is unavailable. Log in and register to view live content