Synonyms
Definition
Reservoir computing is an approach to sequential processing where recurrency is separated from the output mapping (Jaeger, 2003; Maass, Natschlaeger, & Markram, 2002). The input sequence activates neurons in a recurrent neural network (a reservoir, where activity propagates as in a liquid). The recurrent network is large, nonlinear, randomly connected, and fixed. A linear output network receives activation from the recurrent network and generates the output of the entire machine. The idea is that if the recurrent network is large and complex enough, the desired outputs can likely be learned as linear transformations of its activation. Moreover, because the output transformation is linear, it is fast to train. Reservoir computing has been successful in particular in speech and language processing and vision and cognitive neuroscience.
Recommended Reading
Jaeger, H. (2003). Adaptive nonlinear system identification with echo state networks. In S. Becker, S. Thrun, & K. Obermayer (Eds.), Advances in neural information processing systems (Vol. 15, pp. 593–600). Cambridge, MA: MIT Press.
Maass, W., Natschlaeger, T., & Markram, H. (2002). Real-time computing without stable states: A new framework for neural computation based on perturbations. Neural Computation, 14, 2531–2560.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer Science+Business Media, LLC
About this entry
Cite this entry
Miikkulainen, R. (2011). Reservoir Computing. In: Sammut, C., Webb, G.I. (eds) Encyclopedia of Machine Learning. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-30164-8_726
Download citation
DOI: https://doi.org/10.1007/978-0-387-30164-8_726
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-387-30768-8
Online ISBN: 978-0-387-30164-8
eBook Packages: Computer ScienceReference Module Computer Science and Engineering