Attention-Enhanced Reservoir Computing as a Multiple Dynamical System Approximator

Abstract

Reservoir computing has proven effective for tasks such as time-series prediction, particularly in the context of chaotic systems. However, conventional reservoir computing frameworks often face challenges in achieving high prediction accuracy and adapting to diverse dynamical problems due to their reliance on fixed weight structures. A concept of an attention-enhanced reservoir computer has been proposed, which integrates an attention mechanism into the output layer of the reservoir computing model. This addition enables the system to prioritize distinct features dynamically, enhancing adaptability and prediction performance. In this study, we demonstrate the capability of the attention-enhanced reservoir computer to learn and predict multiple chaotic attractors simultaneously with a single set of weights, thus enabling transitions between attractors without explicit retraining. The method is validated using benchmark tasks, including the Lorenz system, R\"ossler system, Henon map, Duffing oscillator, and Mackey-Glass delay-differential equation. Our results indicate that the attention-enhanced reservoir computer achieves superior prediction accuracy, valid prediction times, and improved representation of spectral and histogram characteristics compared to traditional reservoir computing methods, establishing it as a robust tool for modeling complex dynamical systems.