Preprint · 2018 · Open access
Deep Gaussian Processes with Convolutional Kernels
arXiv (Cornell University) · Published 5 June 2018 · DOI 10.48550/arxiv.1806.01655
In brief
“Deep Gaussian Processes with Convolutional Kernels” is a 2018 preprint by Vinayak Kumar and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 40 citations as of 16 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 40
- Most cited in
- 2020 (9)
- References
- 22
- Authors
- 4
Abstract
Deep Gaussian processes (DGPs) provide a Bayesian non-parametric alternative to standard parametric deep learning models. A DGP is formed by stacking multiple GPs resulting in a well-regularized composition of functions. The Bayesian framework that equips the model with attractive properties, such as implicit capacity control and predictive uncertainty, makes it at the same time challenging to combine with a convolutional structure. This has hindered the application of DGPs in computer vision tasks, an area where deep parametric models (i.e. CNNs) have made breakthroughs. Standard kernels used in DGPs such as radial basis functions (RBFs) are insufficient for handling pixel variability in raw images. In this paper, we build on the recent convolutional GP to develop Convolutional DGP (CDGP) models which effectively capture image level features through the use of convolution kernels, therefore opening up the way for applying DGPs to computer vision tasks. Our model learns local spatial influence and outperforms strong GP based baselines on multi-class image classification. We also consider various constructions of convolution kernel over the image patches, analyze the computational trade-offs and provide an efficient framework for convolutional DGP models. The experimental results on image data such as MNIST, rectangles-image, CIFAR10 and Caltech101 demonstrate the effectiveness of the proposed approaches.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Kumar, V., Singh, V. K., Srijith, P. K., & Damianou, A. (2018). Deep Gaussian Processes with Convolutional Kernels. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1806.01655
MLA 9
Kumar, Vinayak, et al. “Deep Gaussian Processes with Convolutional Kernels.” arXiv (Cornell University), 2018. https://doi.org/10.48550/arxiv.1806.01655.
Chicago
Kumar, Vinayak, Vaibhav Kant Singh, P. K. Srijith, and Andreas Damianou. 2018. “Deep Gaussian Processes with Convolutional Kernels.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1806.01655.
Harvard
Kumar, V. et al. (2018) ‘Deep Gaussian Processes with Convolutional Kernels’, arXiv (Cornell University). doi:10.48550/arxiv.1806.01655.
IEEE
V. Kumar, V. K. Singh, P. K. Srijith, and A. Damianou, “Deep Gaussian Processes with Convolutional Kernels,” arXiv (Cornell University), 2018, doi: 10.48550/arxiv.1806.01655.
BibTeX
@misc{kumar2018deep,
title = {{Deep Gaussian Processes with Convolutional Kernels}},
author = {Kumar, Vinayak and Singh, Vaibhav Kant and Srijith, P. K. and Damianou, Andreas},
howpublished = {arXiv (Cornell University)},
year = {2018},
doi = {10.48550/arxiv.1806.01655},
url = {https://doi.org/10.48550/arxiv.1806.01655}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2018 | 2 | |
| 2019 | 7 | |
| 2020 | 9 | |
| 2021 | 6 | |
| 2022 | 6 | |
| 2023 | 2 | |
| 2024 | 4 | |
| 2025 | 2 | |
| 2026 | 2 |
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Gaussian Processes and Bayesian Inference
- deep Gaussian processes
- convolution kernels
- image classification
- Bayesian nonparametric models
- image patches
- computational efficiency
- computer vision
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Kumar, V., Singh, V. K., Srijith, P. K., & Damianou, A. (2018). Deep Gaussian Processes with Convolutional Kernels. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1806.01655
How many times has this paper been cited?
40 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access: read the free full text at arXiv (Cornell University).
Who wrote this paper?
Vinayak Kumar, Vaibhav Kant Singh, P. K. Srijith, Andreas Damianou.
What is the DOI of this paper?
10.48550/arxiv.1806.01655. The permanent link is https://doi.org/10.48550/arxiv.1806.01655.
Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.