How can Nonlinear Dynamics complement Machine Learning?

Machine learning is rapidly evolving and is increasingly being used for developing dynamic models and for analysis and diagnostics. However, these data-based models are often not robust and generalizable. On the other hand, nonlinear dynamics is able to satisfactorily explain many complex phenomena we observe in the physical world. We will explore how these physics-derived insights can help improve data-based models and especially assist diagnostics. Engineering and biomedical applications will be provided to discuss the promising synthesis of nonlinear dynamics and machine learning.

Who Should Attend:

Engineers and scientists who are curious to explore how nonlinear dynamics can contribute to machine learning.

Key Take-away point:

Nonlinear dynamics, which provides the most comprehensive description of dynamical system behavior, can enrich the rapidly evolving field of machine learning.