Infinite Variational Autoencoder for Semi-Supervised Learning
Machine Learning
2016-11-28 v2 Machine Learning
Abstract
This paper presents an infinite variational autoencoder (VAE) whose capacity adapts to suit the input data. This is achieved using a mixture model where the mixing coefficients are modeled by a Dirichlet process, allowing us to integrate over the coefficients when performing inference. Critically, this then allows us to automatically vary the number of autoencoders in the mixture based on the data. Experiments show the flexibility of our method, particularly for semi-supervised learning, where only a small number of training samples are available.
Keywords
Cite
@article{arxiv.1611.07800,
title = {Infinite Variational Autoencoder for Semi-Supervised Learning},
author = {Ehsan Abbasnejad and Anthony Dick and Anton van den Hengel},
journal= {arXiv preprint arXiv:1611.07800},
year = {2016}
}