Corpus ID: 14166286

Sequential Neural Models with Stochastic Layers

@inproceedings{Fraccaro2016SequentialNM,
  title={Sequential Neural Models with Stochastic Layers},
  author={Marco Fraccaro and S{\o}ren Kaae S{\o}nderby and U. Paquet and O. Winther},
  booktitle={NIPS},
  year={2016}
}
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… Expand

Paper Mentions

Stochastic Sequential Neural Networks with Structured Inference
Z-Forcing: Training Stochastic Recurrent Networks
Markov Recurrent Neural Network Language Model
MARKOV RECURRENT NEURAL NETWORKS
  • Che-Yu Kuo, Jen-Tzung Chien
  • Computer Science
  • 2018 IEEE 28th International Workshop on Machine Learning for Signal Processing (MLSP)
  • 2018
Generative Temporal Models with Memory
Recurrent Flow Networks: A Recurrent Latent Variable Model for Spatio-Temporal Density Modelling
Variational Structured Stochastic Network
A recurrent Markov state-space generative model for sequences
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 34 REFERENCES
Learning Stochastic Recurrent Networks
Stochastic Backpropagation and Approximate Inference in Deep Generative Models
Deep Temporal Sigmoid Belief Networks for Sequence Modeling
A Recurrent Latent Variable Model for Sequential Data
Ladder Variational Autoencoders
Neural Variational Inference and Learning in Belief Networks
Auto-Encoding Variational Bayes
...
1
2
3
4
...