How can Nonlinear Dynamics complement Machine Learning? - presented by Prof. C. ‘Nat’ Nataraj

How can Nonlinear Dynamics complement Machine Learning?

Prof. C. ‘Nat’ Nataraj

Prof. C. ‘Nat’ Nataraj
Nonlinear Dynamics
Host
Nonlinear Dynamics, an International Journal of Nonlinear Dynamics and Chaos in Engineering Systems
DateTuesday, March 18, 2025 2:00 PM (UTC)
Live eventThe live event will be accessible via this page.
Nonlinear Dynamics, an International Journal of Nonlinear Dynamics and Chaos in Engineering Systems
How can Nonlinear Dynamics complement Machine Learning?
Prof. C. ‘Nat’ Nataraj
C. ‘Nat’ Nataraj
Villanova University

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.

References
  • 1.
    Zihan Liu et al. (2025) Hybrid Adaptive Modeling using Neural Networks Trained with Nonlinear Dynamics Based Features.
  • 2.
    A. Abbasi et al. (2024) Physics-informed machine learning for modeling multidimensional dynamics. Nonlinear Dynamics
  • 3.
    A. Abbasi et al. (2023) Hybrid modeling of a multidimensional coupled nonlinear system with integration of Hamiltonian mechanics. Nonlinear Dynamics
Grants
    Office of Naval ResearchN000142212480Office of Naval ResearchN000141912070
Date & time
Mar
18
2025
Tuesday, March 18, 2025 2:00 PM to 3:40 PM (UTC)
Details
Listed seminar This seminar is open to all
Recorded Available to all
Q&A Open on this page for 1 day after the seminar
Disclaimer The views expressed in this seminar are those of the speaker and not necessarily those of the journal