Format:
1 Online-Ressource (10 Seiten)
ISSN:
1951-6355
,
1951-6355
Content:
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.
Content:
Peer Reviewed
In:
Heidelberg : Springer, 230,14-15, Seiten 2865-2874, 1951-6355
Language:
English
DOI:
10.1140/epjs/s11734-021-00162-5
URN:
urn:nbn:de:kobv:11-110-18452/27346-4
URL:
Volltext
(kostenfrei)
Bookmarklink
