Author:
Stelzer Florian,Yanchuk Serhiy
Abstract
AbstractA 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.
Funder
Technische Universität Berlin
Publisher
Springer Science and Business Media LLC
Subject
Physical and Theoretical Chemistry,General Physics and Astronomy,General Materials Science
Reference75 articles.
1. G. Stepan, Retarded dynamical systems: stability and characteristic functions (Longman Scientific & Technical, Harlow, 1989)
2. J.K. Hale, S.M.V. Lunel, Introduction to Functional Differential Equations (Springer, New York, 1993)
3. O. Diekmann, S. M. Verduyn Lunel, S. A. van Gils, H.-O. Walther, Delay Equations, Vol. 110. In Applied Mathematical Sciences (Springer, New York, 1995)
4. T. Erneux, Applied Delay Differential Equations, Vol. 3. In Surveys and Tutorials in the Applied Mathematical Sciences (Springer, New York, 2009)
5. H. L. Smith, An Introduction to Delay Differential Equations with Applications to the Life Sciences, Vol. 57 . In Texts in Applied Mathematics (Springer, New York, 2010)
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献