Explore the challenges and limitations of robust Koopman learning in this 27-minute conference talk by Matthew Colbrook from the University of Cambridge. Delivered as part of the Fourth Symposium on Machine Learning and Dynamical Systems at the Fields Institute, delve into the theoretical and practical barriers that researchers face when applying Koopman operator theory to complex dynamical systems. Gain insights into the latest developments in this field and understand the potential implications for future research in machine learning and dynamical systems.
Overview
Syllabus
On the Barriers of Robust Koopman Learning
Taught by
Fields Institute
Related Courses
-
Koopman Operator Theory Based Machine Learning of Dynamical Systems
-
Residual Dynamic Mode Decomposition- Rigorous Data-Driven Computation of Spectral Properties of Koopman Operators for Dynamical Systems
-
Learning Dynamical Systems via Koopman Operator Regression in Reproducing Kernel Hilbert Spaces
-
Koopman Spectral Analysis - Overview
-
Koopman-Based Generalization Bound for Neural Networks
-
The Operator is the Model - Dynamical Systems and Machine Learning
