Reservoir Computing

  • Zoran KonkoliEmail author
Reference work entry
Part of the Encyclopedia of Complexity and Systems Science Series book series (ECSSS)



Contains many parts that interact together. This object can be a mathematical abstraction, but it can also be a real entity, something one can stimulate, observe, or interact with in some other way. Examples: The living cell harbors one million reactions per second. Taken together, the reacting molecules form a system (from a dynamical point of view a rather complicated one); A rock made of atoms is a system (though much simpler than a cell).

Dynamical system

A system that can evolve in time according to a specific set of rules. The time can be either discrete (abrupt changes at specific time instances) or continuous (smooth changes). Without the loss of generality, for simplicity reasons, only deterministic systems will be discussed (no stochastic dynamics).

Configuration or state of the system

The most detailed description of a dynamical system at a given time instance. The appropriate level of such a description depends on what the system is used for. For example, to...


Primary Literature

  1. Appeltant L, Soriano MC, Van der Sande G, Danckaert J, Massar S, Dambre J, Schrauwen B, Mirasso CR, Fischer I (2011) Information processing using a single dynamical node as complex system. Nat Commun 2:468CrossRefGoogle Scholar
  2. Bennett C, Jesorka A, Wendin G, Konkoli Z (2016) On the inverse pattern recognition problem in the context of the time-series data processing with memristor networks. In: Adamatzky J (ed) Advances in Unconventional Computation. Springer, HeidelbergGoogle Scholar
  3. Boyd S, Chua LO (1985) Fading memory and the problem of approximating nonlinear operators with volterra series. IEEE Trans Circuits Syst 32:1150–1161MathSciNetCrossRefGoogle Scholar
  4. Carbajal JP, Dambre J, Hermans M, Schrauwen B (2015) Memristor models for machine learning. Neural Comput 27:725–747CrossRefGoogle Scholar
  5. Dambre J, Verstraeten D, Schrauwen B, Massar S (2012) Information processing capacity of dynamical systems. Sci Rep 2:514CrossRefGoogle Scholar
  6. Goudarzi A, Stefanovic D (2014) Towards a calculus of echo state networks. Procedia Comput Sci 41:176–181CrossRefGoogle Scholar
  7. Jaeger H (2001) The “echo state” approach to analysing and training recurrent neural networks. Technical Report GDM Report 148 (contains errors), German national research center for information technologyGoogle Scholar
  8. Jaeger H (2010) The “echo state” approach to analysing and training recurrent neural networks – with an erratum note. Technical Report erratum to GDM Report 148, German national research center for information technologyGoogle Scholar
  9. Jaeger H, Haas H (2004) Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication. Science 304(5667):78–80CrossRefGoogle Scholar
  10. Joslin D (2006) Real realization: Dennetts real patterns versus putnams ubiquitous automata. Mind Mach 16:29–41CrossRefGoogle Scholar
  11. Kirby K (2009) NACAP 2009 extended abstract: Putnamizing the liquid state. Bloomington, IndianaGoogle Scholar
  12. Konkoli Z (2015) A perspective on Putnam’s realizability theorem in the context of unconventional computation. Int J Unconv Comput 11:83–102Google Scholar
  13. Konkoli Z (2016) On reservoir computing: from mathematical foundations to unconventional applications. In: Adamatzky A (ed) Advances in unconventional computing, volume 1. Theory. Springer, HeidelbergGoogle Scholar
  14. Konkoli Z, Wendin G (2014) On information processing with networks of nanoscale switching elements. Int J Unconv Comput 10(5–6):405–428Google Scholar
  15. Kulkarni MS, Teuscher C (2012) Memristor-based reservoir computing. In: IEEE/ACM international symposium on Nanoscale Architectures (NANOARCH), ACM, New York, pp 226–232Google Scholar
  16. Ladyman J (2009) What does it mean to say that a physical system implements a computation? Theor Comput Sci 410:376–383MathSciNetCrossRefGoogle Scholar
  17. Larger L, Soriano MC, Brunner D, Appeltant L, Gutierrez JM, Pesquera L, Mirasso CR, Fischer I (2012) Photonic information processing beyond Turing: an optoelectronic implementation of reservoir computing. Opt Express 20(3):3241–3249CrossRefGoogle Scholar
  18. Lukoevicius M, Jaeger H (2009) Reservoir computing approaches to recurrent neural network training. Comput Sci Rev 3(3):127–149CrossRefGoogle Scholar
  19. Lukoševičius M, Jaeger H, Schrauwen B (2012) Reservoir computing trends. KI – Knstliche Intelligenz 26(4):365–371Google Scholar
  20. Maass W, Natschlager T, Markram H (2002) Real-time computing without stable states: a new framework for neural computation based on perturbations. Neural Comput 14(11):2531–2560CrossRefGoogle Scholar
  21. Massar M, Massar S (2013) Mean-field theory of echo state networks. Phys Rev E 87:042809CrossRefGoogle Scholar
  22. Mesaritakis C, Bogris A, Kapsalis A, Syvridis D (2015) High-speed all-optical pattern recognition of dispersive Fourier images through a photonic reservoir computing subsystem. Opt Lett 40:3416–3419CrossRefGoogle Scholar
  23. Natschläger T, Maass W, Markram H (2002) The “liquid computer”: A novel strategy for realtime computing on time series (special issue on foundations of information processing). TELEMATIK 8:39–43Google Scholar
  24. Putnam H (1988) Representation and reality. MIT Press, CambridgeGoogle Scholar
  25. Soriano MC, Brunner D, Escalona-Moran M, Mirasso CR, Fischer I (2015) Minimal approach to neuro-inspired information processing. Front Comput Neurosci 9:68CrossRefGoogle Scholar

Books and Reviews

  1. Konkoli (2016); Joslin (2006); Kirby (2009); Boyd and Chua (1985); Putnam (1988); Ladyman (2009)Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Microtechnology and Nanoscience - MC2Chalmers University of TechnologyGothenburgSweden

Personalised recommendations