Machine Learning Potential of a Single Pendulum

Abstract

Reservoir Computing offers a great computational framework where a physical system can directly be used as computational substrate. Typically a "reservoir" is comprised of a large number of dynamical systems, and is consequently high-dimensional. In this work, we use just a single simple low-dimensional dynamical system, namely a driven pendulum, as a potential reservoir to implement reservoir computing. Remarkably we demonstrate, through numerical simulations, as well as a proof-of-principle experimental realization, that one can successfully perform learning tasks using this single system. The underlying idea is to utilize the rich intrinsic dynamical patterns of the driven pendulum, especially the transient dynamics which has so far been an untapped resource. This allows even a single system to serve as a suitable candidate for a "reservoir". Specifically, we analyze the performance of the single pendulum reservoir for two classes of tasks: temporal and non-temporal data processing. The accuracy and robustness of the performance exhibited by this minimal one-node reservoir in implementing these tasks strongly suggest a new direction in designing the reservoir layer from the point of view of efficient applications. Further, the simplicity of our learning system offers an opportunity to better understand the framework of reservoir computing in general and indicates the remarkable machine learning potential of even a single simple nonlinear system.

References in corpus (13)

• Recent Advances in Physical Reservoir Computing: A Review
• Physical reservoir computing -- An introductory perspective
• The Moore-Penrose Pseudoinverse. A Tutorial Review of the Theory
• Large-Scale Optical Reservoir Computing for Spatiotemporal Chaotic Systems Prediction
• Reservoir computing with a single time-delay autonomous Boolean node
• Quantum reservoir computing with a single nonlinear oscillator
• Network Structure Effects in Reservoir Computers
• Physics enhanced neural networks predict order and chaos
• Do Reservoir Computers Work Best at the Edge of Chaos?
• Adaptable Hamiltonian neural networks
• Learning Hamiltonian dynamics by reservoir computer
• Model-free prediction of emergence of extreme events in a parametrically driven nonlinear dynamical system by Deep Learning
• Reservoir Computing based on Quenched Chaos

Cited by in corpus (6)

• Model-free prediction of multistability using echo state network
• Predicting multi-parametric dynamics of externally forced oscillator using reservoir computing and minimal data
• Learning unidirectional coupling using echo-state network
• Role of assortativity in predicting burst synchronization using echo state network
• The Experimental Multi-Arm Pendulum on a Cart: A Benchmark System for Chaos, Learning, and Control
• Predicting the motion of a high-Q pendulum subject to seismic perturbations using machine learning