Explore the concept of Deep Operator Networks (DeepONet) in the context of Physics Informed Machine Learning through this 17-minute video lecture. Delve into the central idea behind DeepONets, understand the solution operator, and examine a practical example application with results. Learn about this innovative approach to machine learning in physics, produced at the University of Washington with funding support from the Boeing Company.
Overview
Syllabus
Intro
DeepONets: Central Idea
// The Strawman
What is the Solution Operator?
// How are DeepONets Trained?
DeepONet Example Application/Results
Outro
Taught by
Steve Brunton
Related Courses
-
Neural Implicit Flow - Physics Informed Machine Learning
-
Neural ODEs - From ResNet to Continuous-Time Machine Learning
-
Designing an Architecture for Physics-Informed Machine Learning - Part 3
-
Machine Learning & Deep Learning in Python & R
-
Physics Informed Neural Networks - Introduction
-
DeepOnet - Learning Nonlinear Operators Based on the Universal Approximation Theorem of Operators
