Explore cutting-edge research on operator learning techniques that eliminate the need for adjoint calculations in this 25-minute conference talk by Nicolas Boulle from the University of Cambridge. Delivered as part of the Fourth Symposium on Machine Learning and Dynamical Systems at the Fields Institute, gain insights into innovative approaches that could potentially revolutionize computational efficiency in machine learning and dynamical systems.
Overview
Syllabus
Operator Learning Without the Adjoint
Taught by
Fields Institute
Related Courses
-
On the Barriers of Robust Koopman Learning
-
The Operator is the Model - Dynamical Systems and Machine Learning
-
Koopman Operator Theory Based Machine Learning of Dynamical Systems
-
Machine Learning for Prediction of Earth Climate and Weather
-
Learning Dynamical Systems via Koopman Operator Regression in Reproducing Kernel Hilbert Spaces
-
Learning from Data (Introductory Machine Learning course)
4.6
