Discrete Variational Autoencoders

Explore this paper's citation graph

Summary

A novel method to train a class of probabilistic models with discrete latent variables using the variational autoencoder framework, including backpropagation through the discrete hidden variables, which outperforms state-of-the-art methods on the permutation-invariant MNIST, Omniglot, and Caltech-101 Silhouettes datasets.

Type
preprint
Published
2016-09-07
Cited by
291
References
62
Access
Open access

Keywords

Probabilistic logic, MNIST database, Artificial intelligence, Autoencoder, Component (thermodynamics)

References

Cited by

Related papers