Fedaux: Leveraging unlabeled auxiliary data in federated learning

F Sattler, T Korjakow, R Rischke… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Federated distillation (FD) is a popular novel algorithmic paradigm for Federated learning
(FL), which achieves training performance competitive to prior parameter averaging-based …

Creinns: Credal-set interval neural networks for uncertainty estimation in classification tasks

K Wang, K Shariatmadar, SK Manchingal, F Cuzzolin… - Neural Networks, 2025 - Elsevier
Effective uncertainty estimation is becoming increasingly attractive for enhancing the
reliability of neural networks. This work presents a novel approach, termed Credal-Set …

Machine learning for health: algorithm auditing & quality control

L Oala, AG Murchison, P Balachandran… - Journal of medical …, 2021 - Springer
Developers proposing new machine learning for health (ML4H) tools often pledge to match
or even surpass the performance of existing tools, yet the reality is usually more …

The Troublesome Kernel: On Hallucinations, No Free Lunches, and the Accuracy-Stability Tradeoff in Inverse Problems

NM Gottschling, V Antun, AC Hansen, B Adcock - SIAM Review, 2025 - SIAM
Methods inspired by artificial intelligence (AI) are starting to fundamentally change
computational science and engineering through breakthrough performance on challenging …

An introduction to optimization under uncertainty--A short survey

K Shariatmadar, K Wang, CR Hubbard… - arxiv preprint arxiv …, 2022 - arxiv.org
Optimization equips engineers and scientists in a variety of fields with the ability to transcribe
their problems into a generic formulation and receive optimal solutions with relative ease …

Dataset similarity to assess semisupervised learning under distribution mismatch between the labeled and unlabeled datasets

S Calderon-Ramirez, L Oala… - IEEE Transactions …, 2022 - ieeexplore.ieee.org
Semisupervised deep learning (SSDL) is a popular strategy to leverage unlabeled data for
machine learning when labeled data is not readily available. In real-world scenarios …

A smoothing interval neural networks-based Caputo fractional-order gradient learning algorithm

Q Shao, Y Liu, R Wang, Y Liu - International Journal of Machine Learning …, 2024 - Springer
Smoothing interval neural networks (SINNs) are widely recognized for their effectiveness in
handling uncertain data across various domains. However, training SINNs using the integer …

Data models for dataset drift controls in machine learning with optical images

L Oala, M Aversa, G Nobis, K Willis… - arxiv preprint arxiv …, 2022 - arxiv.org
Camera images are ubiquitous in machine learning research. They also play a central role
in the delivery of important services spanning medicine and environmental surveying …

[PDF][PDF] PRE-PUBLISHED VERSION

S SECTOR, OF ITU - 2023 - itu.int
Att.1 – TDD update (TG-TM) Page 1 I nternational T elecommunication U nion ITU-Tfg -AI4H
Deliverable TELECOMMUNICATION STANDARDIZATION SECTOR OF ITU 15 September 2023 …

[PDF][PDF] FG-AI4H DEL5. 4 Training and test data specification

S Sector - itu.int
Summary ITU-T FG-AI4H Deliverable DEL5. 4 provides guidelines on the systematic way of
preparing technical requirements specifications for datasets used in the training and testing …