Auxiliary deep generative models
Auxiliary deep generative models
Auxiliary deep generative models

Auxiliary deep generative models

Deep generative models have recently achieved state-of-the-art performance in unsupervised and semi-supervised learning.
Article
Reading time:
By
Lars Maaløe, Casper Kaae Sønderby, Søren Kaae Sønderby, Ole Winther
TABLE OF CONTENTS

Discover Raffle Search

An AI search engine that simplifies data management, analysis, and insights for smarter business decisions and market strategies.
Discover Now

Explore our Research

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, SVHN, and NORB datasets.

Download

Auxiliary deep generative models
Auxiliary deep generative models

Auxiliary deep generative models

Deep generative models have recently achieved state-of-the-art performance in unsupervised and semi-supervised learning.

Explore our Research

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, SVHN, and NORB datasets.

Download

Don't miss any update!
SOC2 badge