Do planetary seasons play a fundamental role in attaining habitable climates?

Research output: Contribution to journalJournal articleResearch

121 Downloads (Pure)

Abstract

Deep generative models parameterized by neural networks have recently achieved state-of-the-art performance in unsupervised and semi-supervised learning. We extend deep generative models with auxiliary variables which improves the variational approximation. The auxiliary variables leave the generative model unchanged but make the variational distribution more expressive. Inspired by the structure of the auxiliary variable we also propose a model with two stochastic layers and skip connections. Our findings suggest that more expressive and properly specified deep generative models converge faster with better results. We show state-of-the-art performance within semi-supervised learning on MNIST (0.96%), SVHN (16.61%) and NORB (9.40%) datasets.
Original languageEnglish
Article numberarXiv:1605.08471
JournalarXiv
Number of pages9
Publication statusPublished - 2016

Bibliographical note

Preliminary work. Under review.

Cite this