Deep Gaussian Process Autoencoders for Novelty Detection
Abstract
Novelty detection is one of the classic problems in machine learning that has applications across several domains. This paper proposes a novel autoencoder based on Deep Gaussian Processes for novelty detection tasks. Learning the proposed model is made tractable and scalable through the use of random feature approximations and stochastic variational inference. The result is a flexible model that is easy to implement and train, and can be applied to general novelty detection tasks, including large-scale problems and data with mixed-type features. The experiments indicate that the proposed model achieves competitive results with state-of-the-art novelty detection methods.
Cite
Text
Domingues et al. "Deep Gaussian Process Autoencoders for Novelty Detection." Machine Learning, 2018. doi:10.1007/S10994-018-5723-3Markdown
[Domingues et al. "Deep Gaussian Process Autoencoders for Novelty Detection." Machine Learning, 2018.](https://mlanthology.org/mlj/2018/domingues2018mlj-deep/) doi:10.1007/S10994-018-5723-3BibTeX
@article{domingues2018mlj-deep,
title = {{Deep Gaussian Process Autoencoders for Novelty Detection}},
author = {Domingues, Remi and Michiardi, Pietro and Zouaoui, Jihane and Filippone, Maurizio},
journal = {Machine Learning},
year = {2018},
pages = {1363-1383},
doi = {10.1007/S10994-018-5723-3},
volume = {107},
url = {https://mlanthology.org/mlj/2018/domingues2018mlj-deep/}
}