Completed
THE GENERAL MACHINE LEARNING (ML) SET UP FOR THIS TALK
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Machine Learning Analysis of Chaos and Vice Versa - Edward Ott, University of Maryland
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 THE GENERAL MACHINE LEARNING (ML) SET UP FOR THIS TALK
- 3 illustrative Example: The Kuramoto-Sivashinsky (KS) Equation The KS equation is a spatiotemporally chaotic system
- 4 Results: Short Term Forecasting of Chaos
- 5 Has the long term dynamical behavior of the Kuramoto-Sivashinsky system truly been replicated? • If it has, even after the sensitive dependence implied by chaos causes prediction to fail, the ergodic…
- 6 Finding Ergodic Properties of a Dynamical System Purely from a Finite Time Series Data String
- 7 Some Tasks that Machine Learning of Ergodic Behavior Might Enable
- 8 Lyapunov exponents provide useful information • The expected duration of useful forecasts of a chaotic process can be estimated as the log of the amount of uncertainty in the specification of initial…
- 9 Lyapunov Exponents for the Example of the KS Equation
- 10 Our Modification of the Lyapunov Exponent Spectrum Remove Red: True KS system two zero
- 11 Why the ML System Does Not See the Galilean Symmetry Associated with the Galilean symmetry is a constant of motion of the KS equation
- 12 Question: Aside from possible corrections for symmetries, does the short term, closed loop forecasting machine learning system always successfully replicate the long term ergodic behavior of the chao…
- 13 EXAMPLE: THE KS EQUATION Prediction succeeds. Replication of long term
- 14 WHEN, HOW, AND WHY IS ERGODIC BEHAVIOR REPLICATED? WHEN, HOW, AND WHY CAN REPLICATION FAIL?
- 15 Outline of Lu et al. Let A denote the attractor of the unknown dynamical system from which the measurements are taken. Lu et al. show that training can ideally lead to the existence of an invariant s…
- 16 GENERALIZED SYNCHRONIZATION AND THE ECHO STATE PROPERTY OF THE OPEN-LOOP CONFIGURATION
