Inferring Global Dynamics of a Black-Box System Using Machine Learning

Abstract

We present that, instead of establishing the equations of motion, one can model-freely reveal the dynamical properties of a black-box system using a learning machine. Trained only by a segment of time series of a state variable recorded at present parameters values, the dynamics of the learning machine at different training stages can be mapped to the dynamics of the target system along a particular path in its parameter space, following an appropriate training strategy that monotonously decreases the cost function. This path is important, because along that, the primary dynamical properties of the target system will subsequently emerge, in the simple-to-complex order, matching closely the evolution law of certain self-evolved systems in nature. Why such a path can be reproduced is attributed to our training strategy. This particular function of the learning machine opens up a novel way to probe the global dynamical properties of a black-box system without artificially establish the equations of motion, and as such it might have countless applications. As an example, this method is applied to infer what dynamical stages a variable star has experienced and how it will evolve in future, by using the light curve observed presently.

17 pages, 8 figures

References in corpus (3)

• Strange nonchaotic stars
• Long time-scale behavior of the Blazhko effect from rectified Kepler data
• Revisiting Evidence of Chaos in X-ray Light Curves: The Case of GRS 1915+105

Cited by in corpus (8)

• Autonomous inference of complex network dynamics from incomplete and noisy data
• Machine Learning of Knot Topology in Non-Hermitian Band Braids
• Machine learning method for ${}^{12}$C event classification and reconstruction in the active target time-projection chamber
• Inferring synchronizability of networked heterogenous oscillators with machine learning
• Energy--Information Trade-off Induces Continuous and Discontinuous Phase Transitions in Lateral Predictive Coding
• Exploring fundamental laws of classical mechanics via predicting the orbits of planets based on neural networks
• Network reconstruction may not mean dynamics prediction
• Network Dynamics-Based Framework for Understanding Deep Neural Networks