Learning Alzheimer's disease signatures by bridging EEG with spiking neural networks and biophysical simulations, the code

The project presents a unified neuromorphic and mechanistic framework for studying Alzheimer’s disease (AD) from resting-state EEG data by combining:

• Spiking Neural Network (SNN)–based EEG classification
• Network-based statistics (NBS) on functional connectivity
• Biophysically grounded spiking network simulations of excitation–inhibition (E/I) imbalance
• Functional connectivity–informed large-scale simulations

The goal is to link data-driven classification with mechanistic modeling, providing interpretable EEG biomarkers grounded in cortical circuit dynamics.

If you use it, please cite  “Linking EEG Functional Connectivity and Excitation–Inhibition Balance to Biophysical Simulation in Alzheimer's Disease” Mamon, Talanov and Crimi 📄 Neurocomputing 2026