Role of assortativity in predicting burst synchronization using echo state network

TL;DR

This paper demonstrates how echo state networks can predict neuronal burst synchronization in scale-free networks, highlighting the impact of network assortativity and node degree on prediction accuracy.

Contribution

It introduces a method using reservoir computing to predict neuronal synchronization and analyzes the influence of network degree correlations on prediction performance.

Findings

ESN can effectively predict burst synchronization with limited nodal input data.

Prediction accuracy varies with network assortativity, favoring low-degree node inputs in assortative networks.

Degree correlation affects the importance of input node selection for synchronization prediction.

Abstract

In this study, we use a reservoir computing based echo state network (ESN) to predict the collective burst synchronization of neurons. Specifically, we investigate the ability of ESN in predicting the burst synchronization of an ensemble of Rulkov neurons placed on a scale-free network. We have shown that a limited number of nodal dynamics used as input in the machine can capture the real trend of burst synchronization in this network. Further, we investigate on the proper selection of nodal inputs of degree-degree (positive and negative) correlated networks. We show that for a disassortative network, selection of different input nodes based on degree has no significant role in machine's prediction. However, in the case of assortative network, training the machine with the information (i.e time series) of low-degree nodes gives better results in predicting the burst synchronization. Finally, we explain the underlying mechanism responsible for observing this differences in prediction in a degree correlated network.