KuraNet: Systems of Coupled Oscillators that Learn to Synchronize

TL;DR

KuraNet is a deep learning system of coupled oscillators that learns to synchronize in disordered networks, enabling analysis of complex dynamical systems with adaptive interactions and broad applicability in physics and biology.

Contribution

It introduces a novel deep learning framework that replaces static couplings with learnable functions, allowing synchronization in heterogeneous and disordered oscillator networks.

Findings

KuraNet can learn data-dependent coupling structures for global or cluster synchrony.

It generalizes across different network scales and data sets.

It effectively explores conditions for synchronization in analytically complex models.

Abstract

Networks of coupled oscillators are some of the most studied objects in the theory of dynamical systems. Two important areas of current interest are the study of synchrony in highly disordered systems and the modeling of systems with adaptive network structures. Here, we present a single approach to both of these problems in the form of "KuraNet", a deep-learning-based system of coupled oscillators that can learn to synchronize across a distribution of disordered network conditions. The key feature of the model is the replacement of the traditionally static couplings with a coupling function which can learn optimal interactions within heterogeneous oscillator populations. We apply our approach to the eponymous Kuramoto model and demonstrate how KuraNet can learn data-dependent coupling structures that promote either global or cluster synchrony. For example, we show how KuraNet can be used to empirically explore the conditions of global synchrony in analytically impenetrable models with disordered natural frequencies, external field strengths, and interaction delays. In a sequence of cluster synchrony experiments, we further show how KuraNet can function as a data classifier by synchronizing into coherent assemblies. In all cases, we show how KuraNet can generalize to both new data and new network scales, making it easy to work with small systems and form hypotheses about the thermodynamic limit. Our proposed learning-based approach is broadly applicable to arbitrary dynamical systems with wide-ranging relevance to modeling in physics and systems biology.