Abstract
Echo state networks are a powerful type of reservoir neural network, but the reservoir is essentially unrestricted in its original formulation. Motivated by limitations in neuromorphic hardware, we remove combinations of the four sources of memory—leaking, loops, cycles, and discrete time—to determine how these influence the suitability of the reservoir. We show that loops and cycles can replicate each other, while discrete time is a necessity. The potential limitation of energy conservation is equivalent to limiting the spectral radius.
This is a preview of subscription content, log in via an institution to check access.
References
Čerňanský, M., Makula, M.: Feed-forward echo state networks. In: Proceedings. 2005 IEEE International Joint Conference on Neural Networks 2005, vol. 3, pp. 1479–1482 (2005)
Čerňanský, M., Tiňo, P.: Comparison of echo state networks with simple recurrent networks and variable-length Markov models on symbolic sequences. In: Sá, J.M., Alexandre, L.A., Duch, W., Mandic, D. (eds.) ICANN 2007. LNCS, vol. 4668, pp. 618–627. Springer, Heidelberg (2007). doi:10.1007/978-3-540-74690-4_63
Jaeger, H.: The “echo state” approach to analysing and training recurrent neural networks. GMD Report (2001)
Lukoševičius, M.: A practical guide to applying echo state networks. In: Montavon, G., Orr, G.B., Müller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, 2nd edn, pp. 659–686. Springer, Heidelberg (2012). doi:10.1007/978-3-642-35289-8_36
Sillin, O.: H., Aguilera, R., Shieh, H.-H., Avizienis, A.V., Aono, M., Stieg, A.Z., Gimzewski, J.K.: A theoretical and experimental study of neuromorphic atomic switch networks for reservoir computing. Nanotechnology 24(38), 384004 (2013)
Werbos, P.J.: Backpropagation through time: what it does and how to do it. Proc. IEEE 78(10), 1550–1560 (1990)
Williams, R.J.: Training recurrent networks using the extended Kalman filter. In: International Joint Conference on Neural Networks 1992. IJCNN, vol. 4, pp. 241–246 (1992)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Stockdill, A., Neshatian, K. (2016). Restricted Echo State Networks. In: Kang, B.H., Bai, Q. (eds) AI 2016: Advances in Artificial Intelligence. AI 2016. Lecture Notes in Computer Science(), vol 9992. Springer, Cham. https://doi.org/10.1007/978-3-319-50127-7_49
Download citation
DOI: https://doi.org/10.1007/978-3-319-50127-7_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-50126-0
Online ISBN: 978-3-319-50127-7
eBook Packages: Computer ScienceComputer Science (R0)