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 computing 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 computing to learn and predict multiple chaotic attractors simultaneously with a single set of weights, thus enabling transitions between attractors without explicit retraining. The main result shows that the attention-enhanced reservoir computing is able to distinguish different attractors just by learning from time-series samples. The method is validated using benchmark tasks, including the Lorenz system, the Rössler system, the Hénon map, the Duffing oscillator, and the Mackey-Glass delay-differential equation. Our results indicate that the attention-enhanced reservoir computing 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.

Close

PrevNext

View figure in article

• Chaos
• Physics of computation
• Chaotic systems
• Chaos & nonlinear dynamics
• Machine learning
• Neural network simulations
• Time series analysis