Journal article · 2022 · Open access

Robustness Analysis of Gaussian Process Convolutional Neural Network with Uncertainty Quantification

Javed, M., Mihaylova, L., Bouaynaya, N.

International Journal of Machine Learning and Computing, 12(5) · Published 25 May 2022 · DOI 10.18178/ijmlc.2022.12.5.1097

Open PDFView at the publisherCite this paper

In brief

“Robustness Analysis of Gaussian Process Convolutional Neural Network with Uncertainty Quantification” is a 2022 journal article by Javed, M. and 2 co-authors, published in International Journal of Machine Learning and Computing. OpenAlex counts 0 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at International Journal of Machine Learning and Computing.

Citations
0
References
28
Authors
3

Abstract

This paper presents a novel framework for image classification which comprises a convolutional neural network (CNN) feature map extractor combined with a Gaussian process (GP) classifier.Learning within the CNN-GP involves forward propagating the predicted class labels, then followed by backpropagation of the maximum likelihood function of the GP with a regularization term added.The regularization term takes the form of one of the three loss functions: the Kullback-Leibler divergence, Wasserstein distance, and maximum correntropy.The training and testing are performed in mini batches of images.The forward step (before the regularization) involves replacing the original images in the mini batch with their close neighboring images and then providing these to the CNN-GP to get the new predictive labels.The network performance is evaluated on MNIST, Fashion-MNIST, CIFAR10, and CIFAR100 datasets.Precision-recall and receiver operating characteristics curves are used to evaluate the performance of the GP classifier.The proposed CNN-GP performance is validated with different levels of noise, motion blur, and adversarial attacks.Results are explained using uncertainty analysis and further tests on quantifying the impact on uncertainty with attack strength are carried out.The results show that the testing accuracy improves for networks that backpropagate the maximum likelihood with regularized losses when compared with methods that do not.Moreover, a comparison with a state-of-art CNN Monte Carlo dropout method is presented.The outperformance of the CNN-GP framework with respect to reliability and computational efficiency is demonstrated.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

M., J., L., M., & N., B. (2022). Robustness Analysis of Gaussian Process Convolutional Neural Network with Uncertainty Quantification. International Journal of Machine Learning and Computing, 12(5). https://doi.org/10.18178/ijmlc.2022.12.5.1097

MLA 9

M., Javed,, et al. “Robustness Analysis of Gaussian Process Convolutional Neural Network with Uncertainty Quantification.” International Journal of Machine Learning and Computing, vol. 12, no. 5, 2022. https://doi.org/10.18178/ijmlc.2022.12.5.1097.

Chicago

M., Javed,, Mihaylova, L., and Bouaynaya, N. 2022. “Robustness Analysis of Gaussian Process Convolutional Neural Network with Uncertainty Quantification.” International Journal of Machine Learning and Computing 12 (5). https://doi.org/10.18178/ijmlc.2022.12.5.1097.

Harvard

M., J., L., M. and N., B. (2022) ‘Robustness Analysis of Gaussian Process Convolutional Neural Network with Uncertainty Quantification’, International Journal of Machine Learning and Computing, 12(5). doi:10.18178/ijmlc.2022.12.5.1097.

IEEE

J. M., M. L., and B. N., “Robustness Analysis of Gaussian Process Convolutional Neural Network with Uncertainty Quantification,” International Journal of Machine Learning and Computing, vol. 12, no. 5, 2022, doi: 10.18178/ijmlc.2022.12.5.1097.

BibTeX

@article{m2022robustness,
  title     = {{Robustness Analysis of Gaussian Process Convolutional Neural Network with Uncertainty Quantification}},
  author    = {M., Javed, and L., Mihaylova, and N., Bouaynaya,},
  journal   = {International Journal of Machine Learning and Computing},
  year      = {2022},
  volume    = {12},
  number    = {5},
  doi       = {10.18178/ijmlc.2022.12.5.1097},
  url       = {https://doi.org/10.18178/ijmlc.2022.12.5.1097}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning

  • Gaussian process classifier
  • convolutional neural networks
  • image classification
  • uncertainty quantification
  • robustness analysis
  • adversarial attacks
  • Kullback-Leibler divergence
  • Wasserstein distance

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

M., J., L., M., & N., B. (2022). Robustness Analysis of Gaussian Process Convolutional Neural Network with Uncertainty Quantification. International Journal of Machine Learning and Computing, 12(5). https://doi.org/10.18178/ijmlc.2022.12.5.1097

How many times has this paper been cited?

0 times, according to OpenAlex on 18 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 at International Journal of Machine Learning and Computing: sign in and open the PDF from this page.

Who wrote this paper?

Javed, M., Mihaylova, L., Bouaynaya, N..

What is the DOI of this paper?

10.18178/ijmlc.2022.12.5.1097, permanently at https://doi.org/10.18178/ijmlc.2022.12.5.1097. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.