Emulating complex networks with a single delay differential equation
Dynamical Systems
2021-06-30 v2
Abstract
A single dynamical system with time-delayed feedback can emulate networks. This property of delay systems made them extremely useful tools for Machine Learning applications. Here we describe several possible setups, which allow emulating multilayer (deep) feed-forward networks as well as recurrent networks of coupled discrete maps with arbitrary adjacency matrix by a single system with delayed feedback. While the network's size can be arbitrary, the generating delay system can have a low number of variables, including a scalar case.
Cite
@article{arxiv.2012.12222,
title = {Emulating complex networks with a single delay differential equation},
author = {Florian Stelzer and Serhiy Yanchuk},
journal= {arXiv preprint arXiv:2012.12222},
year = {2021}
}