Learning Beyond Experience: Generalizing to Unseen State Space with Reservoir Computing

Abstract

Machine learning techniques offer an effective approach to modeling dynamical systems solely from observed data. However, without explicit structural priors -- built-in assumptions about the underlying dynamics -- these techniques typically struggle to generalize to aspects of the dynamics that are poorly represented in the training data. Here, we demonstrate that reservoir computing -- a simple, efficient, and versatile machine learning framework often used for data-driven modeling of dynamical systems -- can generalize to unexplored regions of state space without explicit structural priors. First, we describe a multiple-trajectory training scheme for reservoir computers that supports training across a collection of disjoint time series, enabling effective use of available training data. Then, applying this training scheme to multistable dynamical systems, we show that RCs trained on trajectories from a single basin of attraction can achieve out-of-domain generalization by capturing system behavior in entirely unobserved basins.

18 pages, 12 figures. Updated to include results with RC generalization to unseen segregated and asymmetric basins of attraction and unseen chaotic attractors

References in corpus (10)

• Next Generation Reservoir Computing
• On Explaining the Surprising Success of Reservoir Computing Forecaster of Chaos? The Universal Machine Learning Dynamical System with Contrasts to VAR and DMD
• Parallel Machine Learning for Forecasting the Dynamics of Complex Networks
• Separation of Chaotic Signals by Reservoir Computing
• Robust Forecasting using Predictive Generalized Synchronization in Reservoir Computing
• Learning unseen coexisting attractors
• Catch-22s of reservoir computing
• Machine Learning Link Inference of Noisy Delay-coupled Networks with Opto-Electronic Experimental Tests
• Hybridizing Traditional and Next-Generation Reservoir Computing to Accurately and Efficiently Forecast Dynamical Systems
• Slim Fractals: The Geometry of Doubly Transient Chaos