Explore a comprehensive lecture on learning transfer operators through kernel density estimation, presented by Erik Bollt from Clarkson University at the Fourth Symposium on Machine Learning and Dynamical Systems. Delve into advanced concepts at the intersection of machine learning and dynamical systems, gaining insights into innovative techniques for estimating transfer operators. Discover how kernel density estimation can be applied to enhance understanding and analysis of complex dynamical systems.
Learning Transfer Operators by Kernel Density Estimation
Overview
Syllabus
Learning Transfer Operators by Kernel Density Estimation
Taught by
Fields Institute
Related Courses
-
Statistical Learning of Transfer Operators and the Infinitesimal Generator
-
Basics of Machine Learning
-
Sketching Techniques for Kernel Density Estimation or for Optimal Transport Computations
-
Sketching Techniques for Kernel Density Estimation
-
Probabilistic Graphical Models 3: Learning
-
Data-Adaptive RKHS Regularization for Learning Kernels in Operators
