Abstract
This paper presents the recursive least squares method, combined with the general regression neural networks, applied to solve the problem of learning in time-varying environment. The general regression neural network is based on the orthogonal-type kernel functions. The appropriate algorithm is presented in a recursive form. Sufficient simulations confirm empirically the convergence of the algorithm.
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 subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Albert, A.E., Gardner, L.A.: Stochastic Approximation and Nonlinear Regression, No. 42. MIT Press, Cambridge (1967)
Bilski, J., Rutkowski, L.: A fast training algorithm for neural networks. IEEE Transactions on Circuits and Systems II 45, 749–753 (1998)
Cierniak, R., Rutkowski, L.: On image compression by competitive neural networks and optimal linear predictors. Signal Processing: Image Communication - a Eurasip Journal 15(6), 559–565 (2000)
Gałkowski, T., Rutkowski, L.: Nonparametric recovery of multivariate functions with applications to system identification. Proceedings of the IEEE 73, 942–943 (1985)
Gałkowski, T., Rutkowski, L.: Nonparametric fitting of multivariable functions. IEEE Transactions on Automatic Control AC 31, 785–787 (1986)
Greblicki, W., Pawlak, M.: Nonparametric system indentification. Cambridge University Press (2008)
Greblicki, W., Rutkowska, D., Rutkowski, L.: An orthogonal series estimate of time-varying regression, Tokyo. Annals of the Institute of Statistical Mathematics, vol. 35, Part A, pp. 147–160 (1983)
Greblicki, W., Rutkowski, L.: Density-free Bayes risk consistency of nonparametric pattern recognition procedures. Proceedings of the IEEE 69(4), 482–483 (1981)
Györfi, L., Kohler, M., Krzyżak, A., Walk, H.: A Distribution-Free Theory of Nonparametric Regression. Springer Series in Statistics. Springer, USA (2002)
Nowicki, R.: Nonlinear modelling and classification based on the MICOG defuzzifications. Journal of Nonlinear Analysis, Series A: Theory, Methods and Applications 7(12), 1033–1047 (2009)
Patan, K., Patan, M.: Optimal Training Strategies for Locally Recurrent Neural Networks. Journal of Artificial Intelligence and Soft Computing Research 1(2), 103–114 (2011)
Rafajłowicz, E.: Nonparametric orthogonal series estimators of regression: A class attaining the optimal convergence rate in L 2. Statistics and Probability Letters 5, 219–224 (1987)
Rutkowski, L.: Sequential estimates of probability densities by orthogonal series and their application in pattern classification. IEEE Transactions on Systems, Man, and Cybernetics SMC 10(12), 918–920 (1980)
Rutkowski, L.: Sequential estimates of a regression function by orthogonal series with applications in discrimination, New York, Heidelberg, Berlin. Lectures Notes in Statistics, vol. 8, pp. 236–244 (1981)
Rutkowski, L.: On system identification by nonparametric function fitting. IEEE Transactions on Automatic Control AC 27, 225–227 (1982)
Rutkowski, L.: Orthogonal series estimates of a regression function with applications in system identification. In: Probability and Statistical Inference, pp. 343–347. D. Reidel Publishing Company, Dordrecht (1982)
Rutkowski, L.: On Bayes risk consistent pattern recognition procedures in a quasi-stationary environment. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI 4(1), 84–87 (1982)
Rutkowski, L.: On-line identification of time-varying systems by nonparametric techniques. IEEE Transactions on Automatic Control AC 27, 228–230 (1982)
Rutkowski, L.: On nonparametric identification with prediction of time-varying systems. IEEE Transactions on Automatic Control AC 29, 58–60 (1984)
Rutkowski, L.: Nonparametric identification of quasi-stationary systems. Systems and Control Letters 6, 33–35 (1985)
Rutkowski, L.: The real-time identification of time-varying systems by nonparametric algorithms based on the Parzen kernels. International Journal of Systems Science 16, 1123–1130 (1985)
Rutkowski, L.: A general approach for nonparametric fitting of functions and their derivatives with applications to linear circuits identification. IEEE Transactions Circuits Systems CAS 33, 812–818 (1986)
Rutkowski, L.: Sequential pattern recognition procedures derived from multiple Fourier series. Pattern Recognition Letters 8, 213–216 (1988)
Rutkowski, L.: Nonparametric procedures for identification and control of linear dynamic systems. In: Proceedings of 1988 American Control Conference, June 15-17, pp. 1325–1326 (1988)
Rutkowski, L.: An application of multiple Fourier series to identification of multivariable nonstationary systems. International Journal of Systems Science 20(10), 1993–2002 (1989)
Rutkowski, L.: Nonparametric learning algorithms in the time-varying environments. Signal Processing 18, 129–137 (1989)
Rutkowski, L., Rafajłowicz, E.: On global rate of convergence of some nonparametric identification procedures. IEEE Transaction on Automatic Control AC 34(10), 1089–1091 (1989)
Rutkowski, L.: Identification of MISO nonlinear regressions in the presence of a wide class of disturbances. IEEE Transactions on Information Theory IT 37, 214–216 (1991)
Rutkowski, L.: Multiple Fourier series procedures for extraction of nonlinear regressions from noisy data. IEEE Transactions on Signal Processing 41(10), 3062–3065 (1993)
Rutkowski, L., Gałkowski, T.: On pattern classification and system identification by probabilistic neural networks. Applied Mathematics and Computer Science 4(3), 413–422 (1994)
Rutkowski, L.: A New Method for System Modelling and Pattern Classification. Bulletin of the Polish Academy of Sciences 52(1), 11–24 (2004)
Rutkowski, L., Cpałka, K.: A general approach to neuro-fuzzy systems. In: Proceedings of the 10th IEEE International Conference on Fuzzy Systems, Melbourne, December 2-5, vol. 3, pp. 1428–1431 (2001)
Rutkowski, L., Cpałka, K.: A neuro-fuzzy controller with a compromise fuzzy reasoning. Control and Cybernetics 31(2), 297–308 (2002)
Scherer, R.: Boosting Ensemble of Relational Neuro-fuzzy Systems. In: Rutkowski, L., Tadeusiewicz, R., Zadeh, L.A., Żurada, J.M. (eds.) ICAISC 2006. LNCS (LNAI), vol. 4029, pp. 306–313. Springer, Heidelberg (2006)
Specht, D.F.: Probabilistic neural networks. Neural Networks 3, 109–118 (1990)
Specht, D.F.: A general regression neural network. IEEE Transactions on Neural Networks 2, 568–576 (1991)
Starczewski, J., Rutkowski, L.: Interval type 2 neuro-fuzzy systems based on interval consequents. In: Rutkowski, L., Kacprzyk, J. (eds.) Neural Networks and Soft Computing, pp. 570–577. Physica-Verlag, Springer-Verlag Company, Heidelberg, New York (2003)
Starczewski, J.T., Rutkowski, L.: Connectionist Structures of Type 2 Fuzzy Inference Systems. In: Wyrzykowski, R., Dongarra, J., Paprzycki, M., Waśniewski, J. (eds.) PPAM 2001. LNCS, vol. 2328, pp. 634–642. Springer, Heidelberg (2002)
Szegö, G.: Orthogonal Polynomials, vol. 23. American Mathematical Society Coll. Publ. (1959)
Wilks, S.S.: Mathematical Statistics. John Wiley, New York (1962)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jaworski, M., Gabryel, M. (2012). On Learning in a Time-Varying Environment by Using a Probabilistic Neural Network and the Recursive Least Squares Method. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds) Artificial Intelligence and Soft Computing. ICAISC 2012. Lecture Notes in Computer Science(), vol 7267. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-29347-4_12
Download citation
DOI: https://doi.org/10.1007/978-3-642-29347-4_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-29346-7
Online ISBN: 978-3-642-29347-4
eBook Packages: Computer ScienceComputer Science (R0)