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.

References in corpus (12)

• Deep Learning in Neural Networks: An Overview
• Stable Architectures for Deep Neural Networks
• Strong and weak chaos in nonlinear networks with time-delayed couplings
• Spatio-temporal phenomena in complex systems with time delays
• Multi-clusters in networks of adaptively coupled phase oscillators networks
• Performance boost of time-delay reservoir computing by non-resonant clock cycle
• Temporal dissipative solitons in time-delay feedback systems
• Delayed Dynamical Systems: Networks, Chimeras and Reservoir Computing
• Pattern formation in systems with multiple delayed feedbacks
• Strong and Weak Chaos in Networks of Semiconductor Lasers with Time-delayed Couplings
• Experiments with arbitrary networks in time-multiplexed delay systems
• Discontinuity propagation in delay differential-algebraic equations