arXiv · 2012.12222
Emulating complex networks with a single delay differential equation
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.
Explore related subjects
Keep this discovery
Florian Stelzer, Serhiy Yanchuk. 2020-12-22. Emulating complex networks with a single delay differential equation. https://doi.org/10.1140/epjs/s11734-021-00162-5
Cite the original work for its findings. Save a collection to share your selection of sources.