Reconstruction of the Coupling Architecture in the Ensembles of Radio-Engineering Oscillators by Their Signals Using the Methods of Granger Causality and Partial Directed Coherence

Kornilov, Maksim V.; Sysoev, Ilya V.; Astakhova, D. I.; Kulminsky, Danil D.; Безручко, Б. П.; Ponomarenko, V. I.

doi:10.1007/s11141-021-10078-8

Cited by 2 publications

(2 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[19]. An extension of this approach is the employment of some notion of causality such as Granger causality [20], [21] and short-term causal dependence. [15].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Backpropagation Algorithm for Inferring Disentagled Nodal Dynamics and Connectivity Structure of Dynamical Networks

Tan,

Corrêa,

Stemler

et al. 2024

IEEE Trans. Netw. Sci. Eng.

View full text Add to dashboard Cite

Dynamical networks are versatile models that describe a variety of behaviours such as synchronisation and feedback in networks of coupled dynamical components. However, applying these models in real systems is difficult as prior information of the connectivity structure or local dynamics is often unknown and must be inferred from node state observations. Additionally, the influence of coupling interactions complicates the isolation of local node dynamics. Given the architectural similarities between dynamical networks and recurrent neural networks (RNNs), we propose a network inference method based on the backpropagation through time (BPTT) algorithm used to train RNNs. This method aims to simultaneously infer both the connectivity structure and isolated local node dynamics from node state observations. An approximation of local node dynamics is first constructed using a neural network. This is alternated with an adapted BPTT algorithm to regress corresponding network weights by minimising prediction errors of the network based on the previously constructed local models until convergence. This method was successful in identifying the connectivity structure for coupled networks of chaotic oscillators. Freerun prediction performance with the resulting local models and weights was comparable to the true system with noisy initial conditions. The method is also extended to asymmetric negative coupling.

show abstract

“…[19]. An extension of this approach is the employment of some notion of causality such as Granger causality [20], [21] and short-term causal dependence. [15].…”

Section: Introductionmentioning

confidence: 99%

“…The inference of connectivity structure also poses an additional challenge of false positive couplings and remains an open research area. Granger causality and similar statistical based approaches have been found to particularly struggle with this problem, even for simple network structures such as rings and chains [21], [22].…”

Section: Introductionmentioning

confidence: 99%