Abstract
Echo state network (ESN) is a kind of recurrent neural networks (RNNs) which emphasizes randomly generating large-scale and sparsely connected RNNs coined reservoirs and only training readout weights. First-order reduced and controlled error (FORCE) learning is an effective online training approach for chaotic RNNs. This paper proposes a composite FORCE learning approach enhanced by memory regressor extension to train chaotic ESNs efficiently. In the proposed approach, a generalized prediction error is obtained by using regressor extension and linear filtering operators with memory to retain past excitation information, and the generalized prediction error is applied as additional feedback to update readout weights such that partial parameter convergence can be achieved rapidly even under weak partial excitation. Simulation results based on a dynamics modeling problem indicate that the proposed approach largely improves parameter converging speed and parameter trajectory smoothness compared with the original FORCE learning.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Funahashi, K.I., Nakamura, Y.: Approximation of dynamical systems by continuous time recurrent neural networks. Neural Netw. 6(6), 801–806 (1993)
Werbos, P.J.: Backpropagation through time: what it does and how to do it. Proc. IEEE 78(10), 1550–1560 (1990)
Doya, K.: Bifurcations in the learning of recurrent neural networks. In: IEEE International Symposium on Circuits and Systems, San Diego, CA, pp. 2777–2780 (1992)
Jaeger, H.: Tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the echo state network approach. Technical report, GMD Report 159, German National Research Center for Information Technology, Bonn, Germany (2002)
Chen, G.: A gentle tutorial of recurrent neural network with error backpropagation. arXiv preprint, arXiv:1610.02583 (2016)
Jaeger, H.: The “echo state” approach to analysing and training recurrent neural networks. Technical report, GMD Report 148, German National Research Center for Information Technology, Bonn, Germany (2001)
Maass, W., Natschläger, T., Markram, H.: Real-time computing without stable states: a new framework for neural computation based on perturbations. Neural Comput. 14(11), 2531–2560 (2002)
Steil, J.J.: Backpropagation-decorrelation: online recurrent learning with o(n) complexity. In: IEEE International Joint Conference on Neural Networks, Budapest, Hungary, pp. 843–848 (2004)
Schrauwen, B., Verstraeten, D., Van Campenhout, J.: An overview of reservoir computing: theory, applications and implementations. In: European Symposium on Artificial Neural Networks, pp. 471–482 (2007)
Lukoševičius, M., Jaeger, H.: Reservoir computing approaches to recurrent neural network training. Comput. Sci. Rev. 3(3), 127–149 (2009)
Nakajima, K.: Physical reservoir computing-an introductory perspective. Jpn. J. Appl. Phys. 59(6), Article ID 060501 (2020)
Jaeger, H., Haas, H.: Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication. Science 304(5667), 78–80 (2004)
Jaeger, H.: Adaptive nonlinear system identification with echo state networks. In: International Conference on Neural Information Processing Systems, Cambridge, MA, USA, pp. 609–616 (2002)
Jaeger, H.: Short term memory in echo state networks. Technical report, GMD Report 152, German National Research Center for Information Technology, Bonn, Germany (2002)
Jaeger, H., Lukoševičius, M., Popovici, D., Siewert, U.: Optimization and applications of echo state networks with leaky-integrator neurons. Neural Netw. 20(3), 335–352 (2007)
Bush, K., Anderson, C.: Modeling reward functions for incomplete state representations via echo state networks. In: IEEE International Joint Conference on Neural Networks, Montreal, Canada, pp. 2995–3000 (2005)
Sun, X., Li, T., Li, Q., Huang, Y., Li, Y.: Deep belief echo-state network and its application to time series prediction. Knowl.-Based Syst. 130, 17–29 (2017)
Chen, Q., Shi, H., Sun, M.: Echo state network-based backstepping adaptive iterative learning control for strict-feedback systems: an error-tracking approach. IEEE Trans. Cybern. 50(7), 3009–3022 (2019)
Waegeman, T., Schrauwen, B., et al.: Feedback control by online learning an inverse model. IEEE Trans. Neural Netw. Learn. Syst. 23(10), 1637–1648 (2012)
Deihimi, A., Showkati, H.: Application of echo state networks in short-term electric load forecasting. Energy 39(1), 327–340 (2012)
Ishu, K., van Der Zant, T., Becanovic, V., Ploger, P.: Identification of motion with echo state network. In: Oceans 2004 MTS/IEEE Techno-Ocean 2004 Conference, Kobe, Japan, pp. 1205–1210 (2004)
Skowronski, M.D., Harris, J.G.: Automatic speech recognition using a predictive echo state network classifier. Neural Netw. 20(3), 414–423 (2007)
Sussillo, D., Abbott, L.F.: Generating coherent patterns of activity from chaotic neural networks. Neuron 63(4), 544–557 (2009)
Nicola, W., Clopath, C.: Supervised learning in spiking neural networks with FORCE training. Nat. Commun. 8, Article ID 2208 (2017)
DePasquale, B., Cueva, C.J., Rajan, K., Escola, G.S., Abbott, L.: Full-FORCE: a target-based method for training recurrent networks. PLoS ONE 13(2), Article ID e0191527 (2018)
Inoue, K., Nakajima, K., Kuniyoshi, Y.: Designing spontaneous behavioral switching via chaotic itinerancy. Sci. Adv. 6(46), Article ID eabb3989 (2020)
Tran, Q., Nakajima, K.: Higher-order quantum reservoir computing. arXiv preprint arXiv:2006.08999 (2020)
Sastry, S., Bodson, M.: Adaptive Control: Stability, Convergence and Robustness. Prentice Hall, New Jersey (1989)
Pan, Y., Yu, H.: Composite learning robot control with guaranteed parameter convergence. Automatica 89, 398–406 (2018)
Chowdhary, G., Johnson, E.N.: Theory and flight-test validation of a concurrent-learning adaptive controller. J. Guid. Control. Dyn. 34(2), 592–607 (2011)
Pan, Y., Yu, H.: Composite learning from adaptive dynamic surface control. IEEE Trans. Autom. Control 61(9), 2603–2609 (2016)
Aranovskiy, S., Bobtsov, A., Ortega, R., Pyrkin, A.: Performance enhancement of parameter estimators via dynamic regressor extension and mixing. IEEE Trans. Autom. Control 62(7), 3546–3550 (2017)
Ortega, R., Nikiforov, V., Gerasimov, D.: On modified parameter estimators for identification and adaptive control. A unified framework and some new schemes. Ann. Rev. Control 50, 278–293 (2020)
Pan, Y., Bobtsov, A., Darouach, M., Joo, Y.H.: Learning from adaptive control under relaxed excitation conditions. Int. J. Adapt. Control Signal Process. 33(12), 1723–1725 (2019)
Pan, Y., Sun, T., Liu, Y., Yu, H.: Composite learning from adaptive backstepping neural network control. Neural Netw. 95, 134–142 (2017)
Pan, Y., Yang, C., Pratama, M., Yu, H.: Composite learning adaptive backstepping control using neural networks with compact supports. Int. J. Adapt. Control Signal Process. 33(12), 1726–1738 (2019)
Huang, D., Yang, C., Pan, Y., Cheng, L.: Composite learning enhanced neural control for robot manipulator with output error constraints. IEEE Trans. Industr. Inf. 17(1), 209–218 (2021)
Wu, R., Li, Z., Pan, Y.: Adaptive echo state network robot control with guaranteed parameter convergence. In: International Conference on Intelligent Robotics and Applications, pp. 587–595. Yantai, China (2021)
Acknowledgments
This work was supported in part by the Guangdong Pearl River Talent Program of China under Grant No. 2019QN01X154.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Wu, R., Nakajima, K., Pan, Y. (2021). Performance Improvement of FORCE Learning for Chaotic Echo State Networks. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Lecture Notes in Computer Science(), vol 13109. Springer, Cham. https://doi.org/10.1007/978-3-030-92270-2_23
Download citation
DOI: https://doi.org/10.1007/978-3-030-92270-2_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92269-6
Online ISBN: 978-3-030-92270-2
eBook Packages: Computer ScienceComputer Science (R0)