Deep Convolutional Gaussian Processes

Abstract

We propose deep convolutional Gaussian processes, a deep Gaussian process architecture with convolutional structure. e model is a principled Bayesian framework for detecting hierarchical combinations of local features for image classication. We demonstrate greatly improved image classication performance compared to current Gaussian process approaches on the MNIST and CIFAR-10 datasets. In particular, we improve CIFAR-10 accuracy by over 10 percentage points.

Cite

Text

Blomqvist et al. "Deep Convolutional Gaussian Processes." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2019. doi:10.1007/978-3-030-46147-8_35

Markdown

[Blomqvist et al. "Deep Convolutional Gaussian Processes." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2019.](https://mlanthology.org/ecmlpkdd/2019/blomqvist2019ecmlpkdd-deep/) doi:10.1007/978-3-030-46147-8_35

BibTeX

@inproceedings{blomqvist2019ecmlpkdd-deep,
  title     = {{Deep Convolutional Gaussian Processes}},
  author    = {Blomqvist, Kenneth and Kaski, Samuel and Heinonen, Markus},
  booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
  year      = {2019},
  pages     = {582-597},
  doi       = {10.1007/978-3-030-46147-8_35},
  url       = {https://mlanthology.org/ecmlpkdd/2019/blomqvist2019ecmlpkdd-deep/}
}