Evolution of network structure by temporal learning

TL;DR

This paper investigates how temporal learning rules, inspired by spike-time-dependent plasticity, influence the evolution of network topology, resulting in robust networks with broad degree distributions.

Contribution

It introduces a novel temporal learning rule for network coupling that incorporates competition and demonstrates its impact on network structure evolution.

Findings

Final networks are robust with broad degree distributions.

Learning dynamics significantly shape network topology.

Temporal learning rules induce competitive edge adaptation.

Abstract

We study the effect of learning dynamics on network topology. A network of discrete dynamical systems is considered for this purpose and the coupling strengths are made to evolve according to a temporal learning rule that is based on the paradigm of spike-time-dependent plasticity. This incorporates necessary competition between different edges. The final network we obtain is robust and has a broad degree distribution.