A Framework for Machine Learning of Model Error in Dynamical Systems

Explore a comprehensive framework for machine learning of model error in dynamical systems in this 54-minute lecture from the Santa Fe Institute. Delve into key concepts including linear oscillator examples, partial information, memoryless closure, and hybrid modeling. Examine the differences between discrete and continuous approaches, and gain insights into additive residuals and error epsilon. Discover how this framework can be applied to improve modeling accuracy and predictive capabilities in complex dynamical systems.

Introduction
Machine Learning
Background
The Goal
Linear Oscillator Example
Partial Information
Limiting Sense
First Example
Memoryless Closure
Error Epsilon
Hybrid Modeling
Additive Residuals
Discrete vs Continuous
Notation
Conclusion
Thanks