Attractor reconstruction by machine learning
Abstract
A machine-learning approach called “reservoir computing” has been used successfully for short-term prediction and attractor reconstruction of chaotic dynamical systems from time series data. We present a theoretical framework that describes conditions under which reservoir computing can create an empirical model capable of skillful short-term forecasts and accurate long-term ergodic behavior. We illustrate this theory through numerical experiments. We also argue that the theory applies to certain other machine learning methods for time series prediction.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Jun 01, 2018
- Source ID
- 10.1063/1.5039508
Entities
People
- Brian R. Hunt
- Edward Ott
- Zhixin Lu
Organizations
- Army Research Office
- Defense Advanced Research Projects Agency
- University of Maryland
- University of Pennsylvania