Hybrid models with deep and invertible features
We propose a neural hybrid model consisting of a linear model defined on a set of features computed by a deep, invertible transformation (i.e. a normalizing flow). An attractive property of our model is that both p(features), the density of the features, and p(targets|features), the predictive distr...
| Главные авторы: | , , , , |
|---|---|
| Формат: | Conference item |
| Опубликовано: |
Proceedings of Machine Learning Research
2019
|