Versatile Reservoir Computing for Heterogeneous Complex Networks
This addresses the challenge of maintaining network functionality in complex systems with heterogeneous elements, though it appears incremental as it builds on existing reservoir computing methods.
The authors tackled the problem of sustaining dynamics in heterogeneous complex networks by proposing versatile reservoir computing, which uses a single small-scale reservoir trained on a subset to replicate any element's dynamics and preserve collective dynamics when substituting failed elements, achieving accurate preservation over finite time horizons as validated on three network models.
A new machine learning scheme, termed versatile reservoir computing, is proposed for sustaining the dynamics of heterogeneous complex networks. We show that a single, small-scale reservoir computer trained on time series from a subset of elements is able to replicate the dynamics of any element in a large-scale complex network, though the elements are of different intrinsic parameters and connectivities. Furthermore, by substituting failed elements with the trained machine, we demonstrate that the collective dynamics of the network can be preserved accurately over a finite time horizon. The capability and effectiveness of the proposed scheme are validated on three representative network models: a homogeneous complex network of non-identical phase oscillators, a heterogeneous complex network of non-identical phase oscillators, and a heterogeneous complex network of non-identical chaotic oscillators.