YoVDO

Deep Neural Operators with Reliable Extrapolation for Multiphysics and Multiscale Problems

Offered By: Inside Livermore Lab via YouTube

Tags

Deep Learning Courses Neural Networks Courses Differential Equations Courses Scientific Machine Learning Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore the potential of deep neural networks in learning operators of complex systems in this one-hour webinar on deep neural operators. Delve into the universal approximation theorem of operators and its implications for multiphysics and multiscale problems. Learn about the deep operator network (DeepONet) and its extensions, including DeepM&Mnet, POD-DeepONet, (Fourier-)MIONet, and multifidelity DeepONet. Discover applications in diverse fields such as nanoscale heat transport, bubble growth dynamics, high-speed boundary layers, electroconvection, hypersonics, and geological carbon sequestration. Gain insights into addressing the challenge of extrapolation for deep neural operators, including quantifying extrapolation complexity and developing a complete workflow for reliable extrapolation.

Syllabus

DDPS | Deep neural operators with reliable extrapolation for multiphysics & multiscale problems


Taught by

Inside Livermore Lab

Related Courses

Introduction to Scientific Machine Learning
Purdue University via edX
Scientific Machine Learning: Opportunities and Challenges - Keynote
The Julia Programming Language via YouTube
Scientific Machine Learning - Where Physics-based Modeling Meets Data-driven Learning
Santa Fe Institute via YouTube
AI for Science - Expo Stage Talk - AAAS Annual Meeting
AAAS Annual Meeting via YouTube
Leveraging Physics-Induced Bias in Scientific Machine Learning for Computational Mechanics
Alan Turing Institute via YouTube