Loading...

Composing graphical models with neural networks

6,992 views

Loading...

Loading...

Transcript

The interactive transcript could not be loaded.

Loading...

Rating is available when the video has been rented.
This feature is not available right now. Please try again later.
Published on Nov 13, 2016

Paper: https://arxiv.org/abs/1603.06277
Code: https://github.com/mattjj/svae

How to combine the complementary strengths of probabilistic graphical models and neural networks? We compose latent graphical models with neural network observation likelihoods. For inference, we use recognition networks to produce local evidence potentials, then combine them using efficient message-passing algorithms. All components are trained simultaneously with a single stochastic variational inference objective. We use this framework to automatically segment and categorize mouse behavior from raw depth video.

Matthew Johnson, David Duvenaud, Alex Wiltschko, Bob Datta, Ryan P. Adams
Neural Information Processing Systems, 2016

Loading...


to add this to Watch Later

Add to

Loading playlists...