Neural Implicit Flow - Physics Informed Machine Learning
Offered By: Steve Brunton via YouTube
Course Description
Overview
Explore the concept of Neural Implicit Flow (NIF) in this 14-minute video lecture on Physics Informed Machine Learning. Delve into the underlying principles and discover practical applications such as turbulent data compression and sparse sensor placement. Learn about the mesh-agnostic nature of NIF and examine benchmark results. Gain insights into Shape Net architectures and their relevance to the field. Produced at the University of Washington with funding support from the Boeing Company, this informative presentation offers a comprehensive overview of NIF and its potential impact on physics-based machine learning.
Syllabus
Intro
Underlying Concept
// Example Problem
Example Application: Turbulent Data Compression
Example Application: Sparse Sensor Placement
NIF is Mesh Agnostic
Results/Benchmark Data
// Growing Vortices/ Cool Pictures
Shape Net Architectures
Outro
Taught by
Steve Brunton
Related Courses
Deep Learning to Discover Coordinates for Dynamics - Autoencoders & Physics Informed Machine LearningSteve Brunton via YouTube Machine Learning in Fluid Dynamics and Climate Physics
Alan Turing Institute via YouTube Uncertainty Quantification with Physics-Informed Machine Learning
Alan Turing Institute via YouTube Unique Challenges in Physics-Informed Machine Learning
Alan Turing Institute via YouTube Physics Informed Machine Learning: High-Level Overview of AI and ML in Science and Engineering
Steve Brunton via YouTube