Composing graphical models with neural networks for structured representations and fast inference

@inproceedings{Johnson2016ComposingGM,
  title={Composing graphical models with neural networks for structured representations and fast inference},
  author={Matthew J. Johnson and David K. Duvenaud and Alex Wiltschko and Ryan P. Adams and Sandeep R. Datta},
  booktitle={NIPS},
  year={2016}
}
We propose a general modeling and inference framework that combines the complementary strengths of probabilistic graphical models and deep learning methods. Our model family composes latent graphical models with neural network observation likelihoods. For inference, we use recognition networks to produce local evidence potentials, then combine them with the model distribution using efficient message-passing algorithms. All components are trained simultaneously with a single stochastic… CONTINUE READING
Highly Cited
This paper has 148 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 102 extracted citations

Bayesian Models for Unit Discovery on a Very Low Resource Language

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2018
View 3 Excerpts
Highly Influenced

Disentangled Sequential Autoencoder

View 4 Excerpts
Highly Influenced

Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation

2017 IEEE International Conference on Computer Vision (ICCV) • 2017
View 4 Excerpts
Highly Influenced

149 Citations

0502016201720182019
Citations per Year
Semantic Scholar estimates that this publication has 149 citations based on the available data.

See our FAQ for additional information.

Similar Papers

Loading similar papers…