Discovering Governing Equations for Neural Populations: PEM-UDE with Multiple Shooting for Chaotic Brain Dynamics
Helmut Strey, Chris Rackauckas, Anthony Chesebro
Chaotic neural dynamics resist equation discovery because parameter sensitivity creates intractable optimization landscapes. Using the SciML ecosystem, we combine prediction-error methods with universal differential equations (PEM-UDE) and multiple shooting to tame chaos during learning. In spiking networks, we derive novel mean-field equations for sparse cortical connectivity that predict frequency shifts and synchrony patterns, validated by intracranial recordings.
Methods and Applications of Scientific Machine Learning (SciML)
Room 6