TY - JOUR
T1 - Emulating complex networks with a single delay differential equation
AU - Stelzer, Florian
AU - Yanchuk, Serhiy
N1 - Publisher Copyright:
© 2021, The Author(s).
PY - 2021/10
Y1 - 2021/10
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/85107459857
U2 - 10.1140/epjs/s11734-021-00162-5
DO - 10.1140/epjs/s11734-021-00162-5
M3 - Article
AN - SCOPUS:85107459857
SN - 1951-6355
VL - 230
SP - 2865
EP - 2874
JO - European Physical Journal: Special Topics
JF - European Physical Journal: Special Topics
IS - 14-15
ER -