Abstract
The use of recurrent neural networks in online system identification is very limited in real-world applications, mainly due to the propagation of errors caused by the iterative nature of the prediction task over multiple steps ahead. Bearing this in mind, in this paper, we revisit design issues regarding the robustness of the echo state network (ESN) model in such online learning scenarios using a recursive estimation algorithm and an outlier robust-variant of it. By means of a comprehensive set of experiments, we show that the performance of the ESN is dependent on the adequate choice of the feedback pathways and that the prediction instability is amplified by the norm of the output weight vector, an often neglected issue in related studies.
This study was financed by the following Brazilian research funding agencies: CAPES (finance code 001), FUNCAP (BMD-008-01413.01.02-17) and CNPq (grant 309451/2015-9).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
That of relating asymptotic properties of the excited reservoir dynamics to the driving signal.
References
Atiya, A.F., Parlos, A.G.: New results on recurrent network training: unifying the algorithms and accelerating convergence. IEEE Trans. Neural Netw. 11(3), 697–709 (2000)
Chan, S.C., Zou, Y.X.: A recursive least M-estimate algorithm for robust adaptive filtering in impulsive noise: fast algorithm and convergence performance analysis. IEEE Trans. Sign. Process. 52(4), 975–991 (2004)
Chatzis, S.P., Demiris, Y.: Echo state Gaussian process. IEEE Trans. Neural Netw. 22(9), 1435–1445 (2011)
De Moor, B.L.R.: Daisy: database for the identification of systems. Department of Electrical Engineering, ESAT/SISTA, K.U.Leuven, Belgium. http://www.esat.kuleuven.ac.be/sista/daisy/. Accessed 15 Jan 2019. Used dataset: Dryer: (96–006); Exchanger (97–002); Robot arm (96–009)
Guo, Y., Wang, F., Chen, B., Xin, J.: Robust echo state networks based on correntropy induced loss function. Neurocomputing 267, 295–303 (2017)
Han, M., Xu, M.: Laplacian echo state network for multivariate time series prediction. IEEE Trans. Neural Netw. Learn. Syst. 29(1), 238–244 (2018)
Jaeger, H.: The “echo state” approach to analysing and training recurrent neural networks-with an erratum note. German National Research Center for Information Technology GMD Technical Report 148(34), 13, Bonn, Germany (2001)
Jaeger, H.: Adaptive nonlinear system identification with echo state networks. In: Advances in Neural Information Processing Systems, pp. 609–616 (2003)
Li, D., Han, M., Wang, J.: Chaotic time series prediction based on a novel robust echo state network. IEEE Trans. Neural Netw. Learn. Syst. 23(5), 787–799 (2012)
Lukoševičius, M., Jaeger, H.: Reservoir computing approaches to recurrent neural network training. Comput. Sci. Rev. 3(3), 127–149 (2009)
Shi, Z., Han, M.: Support vector echo-state machine for chaotic time-series prediction. IEEE Trans. Neural Netw. 18(2), 359–372 (2007)
Wigren, T.: Input-output data sets for development and benchmarking in nonlinear identification. Technical Reports from the Department of Information Technology 20, 2010–020 (2010)
Zhang, C., Guo, Y., Wang, F., Chen, B.: Generalized maximum correntropy-based echo state network for robust nonlinear system identification. In: 2018 International Joint Conference on Neural Networks (IJCNN), pp. 1–6. IEEE (2018)
Zhou, H., Huang, J., Lu, F., Thiyagalingam, J., Kirubarajan, T.: Echo state kernel recursive least squares algorithm for machine condition prediction. Mech. Syst. Sign. Process. 111, 68–86 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Bessa, R., Barreto, G.A. (2019). Robust Echo State Network for Recursive System Identification. In: Rojas, I., Joya, G., Catala, A. (eds) Advances in Computational Intelligence. IWANN 2019. Lecture Notes in Computer Science(), vol 11506. Springer, Cham. https://doi.org/10.1007/978-3-030-20521-8_21
Download citation
DOI: https://doi.org/10.1007/978-3-030-20521-8_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-20520-1
Online ISBN: 978-3-030-20521-8
eBook Packages: Computer ScienceComputer Science (R0)