An Introduction to Variational Autoencoders
Abstract
Variational autoencoders provide a principled framework for learning deep latent-variable models and corresponding inference models. In this work, we provide an introduction to variational autoencoders and some important extensions.
- Publication:
-
arXiv e-prints
- Pub Date:
- June 2019
- DOI:
- 10.48550/arXiv.1906.02691
- arXiv:
- arXiv:1906.02691
- Bibcode:
- 2019arXiv190602691K
- Keywords:
-
- Computer Science - Machine Learning;
- Statistics - Machine Learning
- E-Print:
- Foundations and Trends in Machine Learning: Vol. 12 (2019): No. 4, pp 307-392