4 papers
Measurement noise limits the advantage of nonlinear models over linear models in biomedical prediction
Marc-Andre Schulz, Kerstin Ritter
On biomedical tabular data, flexible models such as deep networks, gradient-boosted trees, and kernel methods are repeatedly matched or beaten by linear and logistic regression giv…
Flow Matching with In-Context Priors for Out-of-Distribution Brain Dynamics
Sam Gijsen, MichaÅ Åukomski, Marc-André Schulz +1
Flow matching and diffusion models enable conditional generation across domains ranging from images to proteins, with recent extensions to out-of-distribution contexts. Yet generat…
Brain-Semantoks: Learning Semantic Tokens of Brain Dynamics with a Self-Distilled Foundation Model
Sam Gijsen, Marc-Andre Schulz, Kerstin Ritter
The development of foundation models for functional magnetic resonance imaging (fMRI) time series holds significant promise for predicting phenotypes related to disease and cogniti…
Explainable AI Methods for Neuroimaging: Systematic Failures of Common Tools, the Need for Domain-Specific Validation, and a Proposal for Safe Application
Nys Tjade Siegel, James H. Cole, Mohamad Habes +3
Trustworthy interpretation of deep learning models is critical for neuroimaging applications, yet commonly used Explainable AI (XAI) methods lack rigorous validation, risking misin…