Data Driven Modeling Part III

This talk explores deep learning approaches for modeling dynamical systems, including Physics-Informed Neural Networks (PINNs), Neural ODEs (NODE), and Deep Operator Networks (ONets). We will discuss how we can exploit neural networks to learn and predict the behavior of dynamical systems, either by incorporating dynamics, approximating solution operators, or modeling system evolution directly.

Zoom link: https://www.math.arizona.edu/~klin/rtg-zoom