2 papers
eess.IV2026
Useful nonrobust features are ubiquitous in biomedical images
Coenraad Mouton, Randle Rabe, Niklas C. Koser +4
We study whether deep networks for medical imaging learn useful nonrobust features - predictive input patterns that are not human interpretable and highly susceptible to small adve…
cs.LG2026
KnowIt: Deep Time Series Modeling and Interpretation
M. W. Theunissen, R. Rabe, H. L. Potgieter +1
KnowIt (Knowledge discovery in time series data) is a flexible framework for building deep time series models and interpreting them. It is implemented as a Python toolkit, with sou…