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...
主要な著者: | Eric, N, Matsukawa, A, Teh, Y, Gorur, D, Lakshminarayanan, B |
---|---|
フォーマット: | Conference item |
出版事項: |
Proceedings of Machine Learning Research
2019
|
類似資料
-
Do deep generative models know what they don't know?
著者:: Nalisnick, E, 等
出版事項: (2019) -
Infinite hierarchical hidden Markov models
著者:: Heller, K, 等
出版事項: (2009) -
Indian buffet processes with power-law behavior
著者:: Teh, Y, 等
出版事項: (2009) -
Topology for hybrid trinary multilevel inverter /
著者:: 195523 Chan, Jhan Yhee, 等
出版事項: (2005) -
Stick-breaking construction for the Indian buffet process
著者:: Teh, Y, 等
出版事項: (2007)