Journal article · 2023 · Open access

Uncertainty Estimation in Neural Networks Through Multi-Task Learning

Ashish James, Anusha James

International Journal of Artificial Intelligence & Applications, 14(04), 17–29 · Published 27 July 2023 · DOI 10.5121/ijaia.2023.14402

Open PDFCite this paper

In brief

“Uncertainty Estimation in Neural Networks Through Multi-Task Learning” is a 2023 journal article by Ashish James and Anusha James, published in International Journal of Artificial Intelligence & Applications. OpenAlex counts 0 citations as of 22 November 2026. It is open access: the full text is free to read at International Journal of Artificial Intelligence & Applications.

Citations
0
References
31
Authors
2

Abstract

The impressive predictive performance of deep learning techniques on a wide range of tasks has led to its widespread use. Estimating the confidence of these predictions is paramount for improving the safety and reliability of such systems. However, the uncertainty estimates provided by neural networks (NNs) tend to be overconfident and unreasonable. Previous studies have found out that ensemble of NNs typically produce good predictions and uncertainty estimates. Inspired by these, this paper presents a new framework that can quantitatively estimate the uncertainties by leveraging the advances in multi-task learning through slight modification to the existing training pipelines. This promising algorithm is developed with an intention of deployment in real world problems which already boast a good predictive performance by reusing those pretrained models. The idea is to capture the behavior of the trained NNs for the base task by augmenting it with the uncertainty estimates from a supplementary network. A series of experiments show that the proposed approach produces well calibrated uncertainty estimates with high quality predictions.

Cite this paper

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

APA 7

James, A., & James, A. (2023). Uncertainty Estimation in Neural Networks Through Multi-Task Learning. International Journal of Artificial Intelligence & Applications, 14(04), 17–29. https://doi.org/10.5121/ijaia.2023.14402

MLA 9

James, Ashish, and Anusha James. “Uncertainty Estimation in Neural Networks Through Multi-Task Learning.” International Journal of Artificial Intelligence & Applications, vol. 14, no. 04, 2023, pp. 17–29. https://doi.org/10.5121/ijaia.2023.14402.

Chicago

James, Ashish and Anusha James. 2023. “Uncertainty Estimation in Neural Networks Through Multi-Task Learning.” International Journal of Artificial Intelligence & Applications 14 (04): 17–29. https://doi.org/10.5121/ijaia.2023.14402.

Harvard

James, A. and James, A. (2023) ‘Uncertainty Estimation in Neural Networks Through Multi-Task Learning’, International Journal of Artificial Intelligence & Applications, 14(04), pp. 17–29. doi:10.5121/ijaia.2023.14402.

IEEE

A. James and A. James, “Uncertainty Estimation in Neural Networks Through Multi-Task Learning,” International Journal of Artificial Intelligence & Applications, vol. 14, no. 04, pp. 17–29, 2023, doi: 10.5121/ijaia.2023.14402.

BibTeX

@article{james2023uncertainty,
  title     = {{Uncertainty Estimation in Neural Networks Through Multi-Task Learning}},
  author    = {James, Ashish and James, Anusha},
  journal   = {International Journal of Artificial Intelligence \& Applications},
  year      = {2023},
  volume    = {14},
  number    = {04},
  pages     = {17--29},
  doi       = {10.5121/ijaia.2023.14402},
  url       = {https://doi.org/10.5121/ijaia.2023.14402}
}

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 estimation
  • multi-task learning
  • artificial neural networks
  • overconfidence
  • calibration
  • ensemble methods
  • pre-trained models

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?

James, A., & James, A. (2023). Uncertainty Estimation in Neural Networks Through Multi-Task Learning. International Journal of Artificial Intelligence & Applications, 14(04), 17–29. https://doi.org/10.5121/ijaia.2023.14402

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 International Journal of Artificial Intelligence & Applications: sign in and open the PDF from this page.

Who wrote this paper?

Ashish James, Anusha James.

What is the DOI of this paper?

10.5121/ijaia.2023.14402, permanently at https://doi.org/10.5121/ijaia.2023.14402. 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.