Abstract / Description of output
We develop a framework for incorporating structured graphical models in the encoders of variational autoencoders (VAEs) that allows us to induce interpretable representations through approximate variational inference. This allows us to both perform reasoning (e.g. classification) under the structural constraints of a given graphical model, and use deep generative models to deal with messy, high-dimensional domains where it is often difficult to model all the variation. Learning in this framework is carried out end-to-end with a variational objective, applying to both unsupervised and semi-supervised schemes.
Original language | English |
---|---|
Title of host publication | Interpretable Machine Learning for Complex Systems |
Subtitle of host publication | NIPS 2016 workshop proceedings |
Number of pages | 6 |
Publication status | Published - 8 Dec 2016 |
Event | Interpretable Machine Learning for Complex Systems Workshop: @ NeurIPS 2016 - Barcelona, Spain Duration: 8 Dec 2016 → 8 Dec 2016 https://nips.cc/Conferences/2016/Schedule?showEvent=6238 |
Workshop
Workshop | Interpretable Machine Learning for Complex Systems Workshop |
---|---|
Country/Territory | Spain |
City | Barcelona |
Period | 8/12/16 → 8/12/16 |
Internet address |