DeepAI AI Chat
Log In Sign Up

Sequential Neural Models with Stochastic Layers

by   Marco Fraccaro, et al.

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.


page 1

page 2

page 3

page 4


Learning Stochastic Recurrent Networks

Leveraging advances in variational inference, we propose to enhance recu...

Structured Inference Networks for Nonlinear State Space Models

Gaussian state space models have been used for decades as generative mod...

Stochastic Sequential Neural Networks with Structured Inference

Unsupervised structure learning in high-dimensional time series data has...

Recurrent Neural Networks with Stochastic Layers for Acoustic Novelty Detection

In this paper, we adapt Recurrent Neural Networks with Stochastic Layers...

Think Again Networks and the Delta Loss

This short paper introduces an abstraction called Think Again Networks (...

Edge-based sequential graph generation with recurrent neural networks

Graph generation with Machine Learning is an open problem with applicati...

Re-examination of the Role of Latent Variables in Sequence Modeling

With latent variables, stochastic recurrent models have achieved state-o...

Code Repositories


Code for "Sequential Neural Models with Stochastic Layers"

view repo