Uncertainty-Aware Machine Learning Models for Open-World Decision-Making

Provider

Czech Science Foundation

Programme

Standard projects

Call for proposals

SGA0202600001

Main participants

České vysoké učení technické v Praze / Fakulta elektrotechnická

Contest type

VS - Public tender

Contract ID

26-22444S

Project name in Czech

Uncertainty-Aware Machine Learning Models for Open-World Decision-Making

Annotation in Czech

As artificial intelligence systems play an increasingly central role in decision-making, ensuring their trustworthiness is critical. These systems rely on predictive models trained with machine learning (ML) techniques. For a prediction model to be trustworthy, it must accurately quantify and communicate uncertainty in its predictions, making uncertainty-aware models essential. However, existing ML approaches face significant challenges. Many assume a closed-world scenario, where training data perfectly reflect the deployment environment, while those designed to handle distribution shifts in open-world settings often overlook other types of inherent uncertainties in the data. This project seeks to address these challenges by developing ML methods for learning uncertainty-aware prediction models specifically designed for open-world scenarios, effectively capturing and modeling all sources of uncertainty commonly found in real-world applications.

R&D category

ZV - Basic research

OECD FORD - main branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

OECD FORD - secondary branch

—

OECD FORD - another secondary branch

—

CEP - equivalent branches <br>(according to the <a href="http://www.vyzkum.cz/storage/att/E6EF7938F0E854BAE520AC119FB22E8D/Prevodnik_oboru_Frascati.pdf">converter</a>)

AF - Documentation, librarianship, work with information<br>BC - Theory and management systems<br>BD - Information theory<br>IN - Informatics

Realization period - beginning

Jan 1, 2026

Realization period - end

Dec 31, 2028

Project status

Z - Beginning multi-year project

Latest support payment

—

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Data delivery code

CEP26-GA0-GA-R

Data delivery date

May 6, 2026

Total approved costs

5,919 thou. CZK

Public financial support

5,919 thou. CZK

Other public sources

0 thou. CZK

Non public and foreign sources

0 thou. CZK