This track is dedicated to integrating Explainable AI into computational neuroscience, focusing on its application in interpreting complex brain data such as EEG, fMRI, and invasive recordings. The track aims to showcase the latest advancements in XAI that enhance our understanding of neural processes in constructing brain functioning architecture and identifying crucial neural features in brain disorders. It will highlight the importance of accurate, transparent AI interpretations in neuroscience, addressing both AI’s potential and challenges in unravelling the complexities of brain data for scientific and medical advancements.
Topics
| Explainable AI in Neuroimaging: Interpretable Models vs. Black Box Approaches |
| Feature-based Attributions and Brain Atlases |
| XAI Techniques for Reconstructing Visual Stimuli from Neural Data |
| Enhancing Neurofeedback with Explainable Machine Learning |
| Explainable Spike Representation and Sorting |
| Predictive Modeling in Cognitive Neuroscience using XAI |
| XAI-driven Behavioural Neurostimulation |
| Privacy and Ethics in AI-Driven Neurological Data Analysis |
| Real-Time EEG Data Processing with XAI Methods |
| Neuro-symbolic-driven Latent Feature Disentanglement for neuroimaging |
| Interpretable Sleep-State Decoding |
| Identifying Neurological Biomarkers through Explainable Machine Learning |
