no code implementations • 23 May 2024 • Kaizheng Wang, Fabio Cuzzolin, Keivan Shariatmadar, David Moens, Hans Hallez
This paper presents an innovative approach, called credal wrapper, to formulating a credal set representation of model averaging for Bayesian neural networks (BNNs) and deep ensembles, capable of improving uncertainty estimation in classification tasks.
no code implementations • 10 Jan 2024 • Kaizheng Wang, Keivan Shariatmadar, Shireen Kudukkil Manchingal, Fabio Cuzzolin, David Moens, Hans Hallez
Uncertainty estimation is increasingly attractive for improving the reliability of neural networks.
no code implementations • 11 Jul 2023 • Shireen Kudukkil Manchingal, Muhammad Mubashar, Kaizheng Wang, Keivan Shariatmadar, Fabio Cuzzolin
Machine learning is increasingly deployed in safety-critical domains where robustness against adversarial attacks is crucial and erroneous predictions could lead to potentially catastrophic consequences.
no code implementations • 1 Dec 2022 • Keivan Shariatmadar, Kaizheng Wang, Calvin R. Hubbard, Hans Hallez, David Moens
The goal of this survey paper is to briefly touch upon the state of the art in a variety of different methods and refer the reader to other literature for more in-depth treatments of the topics discussed here.