Dissertation · 2026 · Open access

Uncertainty Quantification in Deep Neural Networks

Carol Eunice Gudumotu, Arash Sarshar

Zenodo (CERN European Organization for Nuclear Research) · Published 3 August 2026 · DOI 10.5281/zenodo.21765337

Open full textCite this paper

In brief

“Uncertainty Quantification in Deep Neural Networks” is a 2026 dissertation by Carol Eunice Gudumotu and Arash Sarshar, published in Zenodo (CERN European Organization for Nuclear Research). OpenAlex counts 0 citations as of 22 November 2026. It is open access under a CC BY licence: the full text is free to read at Zenodo (CERN European Organization for Nuclear Research).

Citations
0
Authors
2

Abstract

The emergence of deep learning has significantly impacted many industries such as healthcare,automotive, and marketing. However, in risk-critical sectors, merely forecasting outcomes does notsuffice; it is imperative that the machine learning models also provide insights into the level ofuncertainty associated with each prediction. In this research endeavor, we introduce a pioneeringdeep learning-based framework termed Bayesian deep operator neural networks, specificallydesigned to estimate both aleatoric and epistemic uncertainties, accounting for both modeluncertainty and input noise. Through extensive experimentation, our findings demonstrate that thisframework surpasses existing models by exhibiting superior performance in different criteria suchas robustness, accuracy, and reliable uncertainty quantification

Cite this paper

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

APA 7

Gudumotu, C. E., & Sarshar, A. (2026). Uncertainty Quantification in Deep Neural Networks. Zenodo (CERN European Organization for Nuclear Research). https://doi.org/10.5281/zenodo.21765337

MLA 9

Gudumotu, Carol Eunice, and Arash Sarshar. “Uncertainty Quantification in Deep Neural Networks.” Zenodo (CERN European Organization for Nuclear Research), 2026. https://doi.org/10.5281/zenodo.21765337.

Chicago

Gudumotu, Carol Eunice and Arash Sarshar. 2026. “Uncertainty Quantification in Deep Neural Networks.” Zenodo (CERN European Organization for Nuclear Research). https://doi.org/10.5281/zenodo.21765337.

Harvard

Gudumotu, C. E. and Sarshar, A. (2026) ‘Uncertainty Quantification in Deep Neural Networks’, Zenodo (CERN European Organization for Nuclear Research). doi:10.5281/zenodo.21765337.

IEEE

C. E. Gudumotu and A. Sarshar, “Uncertainty Quantification in Deep Neural Networks,” Zenodo (CERN European Organization for Nuclear Research), 2026, doi: 10.5281/zenodo.21765337.

BibTeX

@phdthesis{gudumotu2026uncertainty,
  title     = {{Uncertainty Quantification in Deep Neural Networks}},
  author    = {Gudumotu, Carol Eunice and Sarshar, Arash},
  year      = {2026},
  doi       = {10.5281/zenodo.21765337},
  url       = {https://doi.org/10.5281/zenodo.21765337}
}

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

  • uncertainty quantification
  • Bayesian neural networks
  • aleatoric uncertainty
  • epistemic uncertainty
  • model uncertainty
  • input noise
  • robustness

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?

Gudumotu, C. E., & Sarshar, A. (2026). Uncertainty Quantification in Deep Neural Networks. Zenodo (CERN European Organization for Nuclear Research). https://doi.org/10.5281/zenodo.21765337

How many times has this paper been cited?

0 times, according to OpenAlex on 22 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 Zenodo (CERN European Organization for Nuclear Research): sign in and open the full text from this page.

Who wrote this paper?

Carol Eunice Gudumotu, Arash Sarshar.

What is the DOI of this paper?

10.5281/zenodo.21765337, permanently at https://doi.org/10.5281/zenodo.21765337. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 22 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.