Uncertainty Quantification and Robustness in Modern Artificial Intelligence
A special issue of Entropy (ISSN 1099-4300). This special issue belongs to the section "Multidisciplinary Applications".
Deadline for manuscript submissions: 31 July 2026
Special Issue Editor
Special Issue Information
Dear Colleagues,
Uncertainty quantification is garnering more interest within the machine learning and artificial intelligent communities, with a growing number of researchers realising how important it is for AI models to be aware of any uncertainty affecting their predictions and decisions. This can be induced by an insufficient quantity or quality of the training data, shifts in data domain distributions, or the misspecification of the hypothesis space itself or of the learnt feature representation. A variety of approaches have been proposed, including ensemble methods, Bayesian deep learning, evidential neural networks, interval methods, and approaches leveraging second-order uncertainty representations such as credal and random sets. However, fundamental issues remain, such as how to decouple aleatoric from epistemic uncertainty, what the implications of uncertainty quantification are for statistical learning, and how uncertainty-aware models should be evaluated, just to name a few. We would like to invite authors to submit their original work, discussing new approaches to quantifying uncertainty in AI in terms of representation, architecture or loss design. This includes frameworks for a fair evaluation of the outcomes, robustness, dominance and other theoretical results and implications for active learning, safety, experimental design, calibration, out-of-distribution detection, model adaptation or statistical learning. We also welcome empirical papers that propose new datasets for uncertainty-aware prediction or solutions to real-world applications.
Prof. Dr. Fabio Cuzzolin
Guest Editor
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Entropy is an international peer-reviewed open access monthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
Keywords
- epistemic and aleatoric uncertainty
- uncertainty quantification
- bayesian deep learning
- calibration
- robustness
- statistical learning
- generalisation
- model adaptation
- safety
Benefits of Publishing in a Special Issue
- Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
- Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
- Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
- External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
- Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.
Further information on MDPI's Special Issue policies can be found here.
