Deep Representation Learning for Dynamical Systems Modeling
This work addresses the challenge of accurate dynamics modeling for chaotic systems, which is important for fields like physics and engineering, but it is incremental as it applies an existing method to a new domain.
The authors tackled the problem of modeling chaotic dynamical systems by adapting the Transformer model to learn state representations, achieving promising results in trajectory generation and approximating attractor characteristics like state distribution and Lyapunov exponent.
Proper states' representations are the key to the successful dynamics modeling of chaotic systems. Inspired by recent advances of deep representations in various areas such as natural language processing and computer vision, we propose the adaptation of the state-of-art Transformer model in application to the dynamical systems modeling. The model demonstrates promising results in trajectories generation as well as in the general attractors' characteristics approximation, including states' distribution and Lyapunov exponent.