Abstract
A function for generating temporal patterns such as melody of the music and motor commands for body movements is one of major roles in the brain. In this paper, we study how such temporal patterns can be generated from nonlinear dynamics of recurrent neural networks (RNNs) and clarify the hidden mechanism that supports the functional ability of RNNs from reservoir computing (RC) approach. We show that when the reservoir (random recurrent neural network) shows weak instability to initial conditions, the error of the output from the reservoir and the target pattern is sufficiently small and robust to noise. It is also shown that the output from the spontaneous activity of the trained system intermittently exhibits response-like activity to the trigger input, which may be related to recent experimental findings in the neuroscience.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Tsuda, I.: Behavioral and Brain Sciences 24, 793–810 (2001)
Sompolinsky, H., Crisanti, A., Sommers, H.J.: Phys. Rev. Lett. 61, 259 (1988)
Maas, W., Natschläger, T., Markam, H.: Neural Comp. 14, 2351 (2002)
Jaeger, H., Haas, H.: Science 304, 78 (2004)
Sussillo, D., Abbott, L.F.: Neuron 63, 544 (2009)
Costa, U.M.S., Lyra, M.L., Plastino, A.R., Tsallis, C.: Phys. Rev. E 56, 245 (1997)
Arieli, A., Sterkin, A., Grinvald, A., Aertsen, A.: Science 273, 1868 (1996)
Kenet, T., Bibitchko, D., Tsodyks, M., Grinvald, A., Arieli, A.: Nature 425, 954 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Suetani, H. (2015). Weak Sensitivity to Initial Conditions for Generating Temporal Patterns in Recurrent Neural Networks: A Reservoir Computing Approach. In: Sanayei, A., E. Rössler, O., Zelinka, I. (eds) ISCS 2014: Interdisciplinary Symposium on Complex Systems. Emergence, Complexity and Computation, vol 14. Springer, Cham. https://doi.org/10.1007/978-3-319-10759-2_6
Download citation
DOI: https://doi.org/10.1007/978-3-319-10759-2_6
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-10758-5
Online ISBN: 978-3-319-10759-2
eBook Packages: EngineeringEngineering (R0)