| Abstract: |
| With the development of machine learning techniques, data-driven approaches are becoming increasingly important in real-world modeling with stochastic dynamical systems. However, in the field of neural science problems, these approaches are still in their early stages. We first review some neural inverse problems to deepen the understanding of neural dynamics in complex brain systems. Then we propose some applications to model tipping phenomena and optimal control in brain diseases. The methods include large deviation theory, optimal control, and Schrodinger bridge. |
|