Our recent work has demonstrated that accurate surrogate models for single neurons can be achieved using Neural ODEs and latent representations. However, biophysically detailed brain simulations still rely on ODE-based methods that are computationally prohibitive in terms of speed, memory, and scalability when extended to large networks. This thesis focuses on the next critical step: developing surrogate models for coupled neuronal networks, capturing interactions, synchronization, and emergent dynamics in a shared latent space. The goal is to enable efficient, scalable brain simulations, moving toward real-time and large-scale Digital Brain Twin applications.
IMPORTANT: When applying for a thesis, always attach your CV, course list and course grades to your application so as to ensure best fit with the topic at hand!