Abstract
In the paper convergence of the RBF network regression estimates and classifiers with so-called regular radial kernels is investigated. The parameters of the network are trained by minimizing the empirical risk on the training data. We analyze MISE convergence by utilizing the machine learning theory techniques such as VC dimension and covering numbers and the error bounds involving them. The performance of the normalized RBF network regression estimates is also tested in simulations.
A. Krzyżak—Research of the first author was supported by the Alexander von Humboldt Foundation and the Natural Sciences and Engineering Research Council of Canada under Grant RGPIN-2015-06412. He carried out this research at the Westpomeranian University of Technology during his sabbatical leave from Concordia University.
T. Gałkowski—Research of the second author was supported by the project financed with the program of the Polish Minister of Science and Higher Education under the name “Regional Initiative of Excellence" in the years 2019 - 2022 project number 020/RID/2018/19 the amount of financing 12,000,000 PLN.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Anthony, M., Bartlett, P.L.: Neural Network Learning: Theoretical Foundations. Cambridge University Press, Cambridge (1999)
Barron, A.R.: Universal approximation bounds for superpositions of a sigmoidal function. IEEE Trans. Inf. Theory 39, 930–945 (1993)
Bauer, B., Kohler, M.: On deep learning as a remedy for the curse of dimensionality in nonparametric regression. Ann. Stat. 47(4), 2261–2285 (2019)
Beirlant, J., Györfi, L.: On the asymptotic \({L}_2\)-error in partitioning regression estimation. J. Stat. Plan. Inference 71, 93–107 (1998)
Bologna, G., Hayashi, Y.: Characterization of symbolic rules embedded in deep DIMLP networks: a challenge to transparency of deep learning. J. Artifi. Intell. Soft Comput. 7(4), 265–286 (2017)
Breiman, L.: Random forests. Mach. Learn. 45, 5–32 (2001)
Breiman, L., Friedman, J.H., Olshen, R.A., Stone, C.J.: Classification and Regression Trees, Wadsworth Advanced Books and Software, CA, Belmont (1984)
Broomhead, D.S., Lowe, D.: Multivariable functional interpolation and adaptive networks. Complex Syst. 2, 321–323 (1988)
Cybenko, G.: Approximations by superpositions of sigmoidal functions. Math. Control Signals Syst. 2, 303–314 (1989)
Biau, G., Devroye, L.: Lectures on the Nearest Neighbor Method. SSDS, Springer, Cham (2015). https://doi.org/10.1007/978-3-319-25388-6
Devroye, L., Györfi, L., Lugosi, G.: Probabilistic Theory of Pattern Recognition. Springer-Verlag, New York (1996). https://doi.org/10.1007/978-1-4612-0711-5
Devroye, L., Györfi, L., Krzyżak, A., Lugosi, G.: On the strong universal consistency of nearest neighbor regression function estimates. Ann. Stat. 22, 1371–1385 (1994)
Devroye, L., Krzyżak, A.: An equivalence theorem for \(L_1\) convergence of the kernel regression estimate. J. Stat. Plan. Inference 23, 71–82 (1989)
Devroye, L.P., Wagner, T.J.: Distribution-free consistency results in nonparametric discrimination and regression function estimation. Ann. Stat. 8, 231–239 (1980)
Duda, P., Rutkowski, L., Jaworski, M., Rutkowska, D.: On the Parzen kernel-based probability density function learning procedures over time-varying streaming data with applications to pattern classification. IEEE Trans. Cybern. 50(4), 1683–1696 (2020)
Duda, R., Hart, P., Stork, D.: Pattern Classification, Wiley, 2nd ed. (2001)
Gałkowski, T., Krzyżak, A., Patora-Wysocka, Z., Filutowicz, Z., Wang, L.: A new approach to detection of changes in multidimensional patterns - Part II. J. Artifi. Intell. Soft Comput. Res. 11(3), 217–227 (2021)
Girosi, F., Anzellotti, G.: Rates of convergence for radial basis functions and neural networks. In: Mammone, R.J. (ed.) Artificial Neural Networks for Speech and Vision, pp. 97–113. Chapman and Hall, London (1993)
Girosi, F., Jones, M., Poggio, T.: Regularization theory and neural network architectures. Neural Comput. 7, 219–267 (1995)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. The MIT Press (2016)
Greblicki, W.: Asymptotically Optimal Probabilistic Algorithms for Pattern Recognition and Identification. Monografie No. 3. Prace Naukowe Instytutu Cybernetyki Technicznej Politechniki Wroclawskiej, Nr. 18. Wroclaw, Poland (1974)
Gramacki, A., Gramacki, J.: FFT-based fast bandwidth selector for multivariate kernel density estimation. Comput. Stat. Data Anal. 106, 27–45 (2017)
Greblicki, W., Pawlak, M.: Fourier and Hermite series estimates of regression functions. Ann. Inst. Stat. Math. 37, 443–454 (1985)
Greblicki, W., Pawlak, M.: Necessary and sufficient conditions for Bayes risk consistency of a recursive kernel classification rule. IEEE Trans. Inf. Theory IT-33, 408–412 (1987)
Györfi, L., Kohler, M., Krzyżak, A., Walk, H.: A Distribution-Free Theory of Nonparametric Regression. Springer Verlag, New York (2002). https://doi.org/10.1007/b97848
Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning. SSS, Springer, New York (2009). https://doi.org/10.1007/978-0-387-84858-7
Haykin, S.O.: Neural Networks and Learning Machines, 3rd edn. Prentice-Hall, New York (2008)
Homenda, W., Jastrzȩbska, A., Pedrycz, W., Yu, F.: Combining classifiers for foreign pattern rejection. J. Artif. Intell. Soft Comput. Res. 10(2), 75–94 (2020)
Hornik, K., Stinchocombe, S., White, H.: Multilayer feed-forward networks are universal approximators. Neural Netw. 2, 359–366 (1989)
Jordanov, I., Petrov, N., Petrozziello, A.: Classifiers accuracy improvement based on missing data imputation. J. Artifi. Intell. Soft Comput. 8(8), 31–48 (2018)
Kohler, M., Krzyżak, A.: Nonparametric regression based on hierarchical interaction models. IEEE Trans. Inf. Theory 63, 1620–1630 (2017)
Krzyżak, A.: The rates of convergence of kernel regression estimates and classification rules. IEEE Trans. Inf. Theory IT-32, 668–679 (1986)
Krzyżak, A.: Global convergence of recursive kernel regression estimates with applications in classification and nonlinear system estimation. IEEE Trans. Inf. Theory IT-38, 1323–1338 (1992)
Krzyżak, A., Linder, T., Lugosi, G.: Nonparametric estimation and classification using radial basis function nets and empirical risk minimization. IEEE Trans. Neural Netw. 7(2), 475–487 (1996)
Krzyżak, A., Linder, T.: Radial basis function networks and complexity regularization in function learning. IEEE Trans. Neural Netw. 9(2), 247–256 (1998)
Krzyżak, A., Niemann, H.: Convergence and rates of convergence of radial basis functions networks in function learning. Nonlinear Anal. 47, 281–292 (2001)
Krzyżak, A., Partyka, M.: Convergence and rates of convergence of normalized recursive radial basis functions networks in function learning and classification. In: Proceedings of 16th International Conference on Artificial Intelligence and Soft Computing, Zakopane, Poland, 11–15 June 2017. Lecture Notes on Artificial Intelligence and Soft Computing, Part I, LNAI, vol. 10245, pp. 107–117. Springer-Verlag, (2017)
Krzyżak, A., Partyka, M.: Learning and convergence of the normalized radial basis functions networks. In: Rutkowski, L., Scherer, R., Korytkowski, M., Pedrycz, W., Tadeusiewicz, R., Zurada, J.M. (eds.) ICAISC 2018. LNCS (LNAI), vol. 10841, pp. 118–129. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-91253-0_12
Krzyżak, A., Partyka, M.: On Learning and convergence of rbf networks in regression estimation and classification. In: Rutkowski, L., Scherer, R., Korytkowski, M., Pedrycz, W., Tadeusiewicz, R., Zurada, J.M. (eds.) ICAISC 2019. LNCS (LNAI), vol. 11508, pp. 131–142. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-20912-4_13
Krzyżak, A., Pawlak, M.: Distribution-free consistency of a nonparametric kernel regression estimate and classification. IEEE Trans. Inf. Theory IT-30, 78–81 (1984)
Krzyżak, A., Schäfer, D.: Nonparametric regression estimation by normalized radial basis function networks. IEEE Trans. Inf. Theory 51, 1003–1010 (2005)
Lv, J., Pawlak, M.: Bandwidth selection for kernel generalized regression neural networks in identification of Hammerstein systems. J. Artifi. Intell. Soft Comput. Res. 11(3), 181–194 (2021)
Lugosi, G., Zeger, K.: Nonparametric estimation via empirical risk minimization. IEEE Trans. Inf. Theory 41, 677–687 (1995)
Mikołajczyk, A., Grochowski, M., Kwasigroch, A.: Towards explainable classifiers using the counterfactual approach - global explanations for discovering bias in data. J. Artif. Intell. Soft Comput. Res. 11(1), 51–67 (2021)
Moody, J., Darken, J.: Fast learning in networks of locally-tuned processing units. Neural Comput. 1, 281–294 (1989)
Nadaraya, E.A.: On estimating regression. Theory Probability Appli. 9, 141–142 (1964)
Nowicki, R.K., Grzanek, K., Hayashi, Y.: Rough support vector machine for classification with interval and incomplete data. J. Artif. Intell. Soft Comput. Res. 10(1), 47–56 (2020)
Park, J., Sandberg, I.W.: Universal approximation using Radial-Basis-Function networks. Neural Comput. 3, 246–257 (1991)
Park, J., Sandberg, I.W.: Approximation and radial-basis-function networks. Neural Comput. 5, 305–316 (1993)
Pietruczuk, L., Rutkowski, L., Jaworski, M., Duda, P.: The Parzen kernel approach to learning in non-stationary environment. In: Proceedings 2014 International Joint Conference on Neural Networks (IJCNN), pp. 3319–3323 (2014)
Pollard, D.: Convergence of Stochastic Processes. Springer Verlag, New York (1984). https://doi.org/10.1007/978-1-4612-5254-2
Rafajłowicz, W.: Learning novelty detection outside a class of random curves with application to COVID-19 growth. J. Artif. Intell. Soft Comput. Res. 11(3), 195–215 (2021)
Ripley, B.D.: Pattern Recognition and Neural Networks. Cambridge University Press, Cambridge (2008)
Rutkowski, L.: Identification of MISO nonlinear regressions in the presence of a wide class of disturbances. IEEE Trans. Inf. Theory 37(1), 214–216 (1991)
Rutkowski, L.: Adaptive probabilistic neural networks for pattern classification in time-varying environment. IEEE Trans. Neural Networks 15(4), 811–827 (2004)
Samworth, R.J., Wand, M.P.: Asymptotics and optimal bandwidth selection for highest density region estimation. Ann. Stat. 38(3), 1767–1792 (2010)
Scornet, E., Biau, G., Vert, J.-P.: Consistency of random forest. Ann. Stat. 43(4), 1716–1741 (2015)
Shorten, R., Murray-Smith, R.: Side effects of normalising radial basis function networks. Int. J. Neural Syst. 7, 167–179 (1996)
Specht, D.F.: Probabilistic neural networks. Neural Netw. 3, 109–118 (1990)
Vapnik, V.N., Chervonenkis, A.Y.: On the uniform convergence of relative frequencies of events to their probabilities. Theory Probab. Appli. 16, 264–280 (1971)
Vapnik, V.: Estimation of Dependences Based on Empirical Data. ISS, Springer, New York (2006). https://doi.org/10.1007/0-387-34239-7
van de Geer, S.: Empirical Processes in M-Estimation. Cambridge University Press, New York (2000)
Watson, G.S.: Smooth regression analysis, Sankhya Series A, vol. 26, pp. 359–372
White, H.: Connectionist nonparametric regression: multilayer feedforward networks that can learn arbitrary map**s. Neural Netw. 3, 535–549 (1990)
Wolverton, C.T., Wagner, T.J.: Asymptotically optimal discriminant functions for pattern classification. IEEE Trans. Inf. Theory IT-15 258–265 (1969)
Xu, L., Krzyżak, A., Yuille, A.L.: On radial basis function nets and kernel regression: approximation ability, convergence rate and receptive field size. Neural Netw. 7, 609–628 (1994)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Krzyżak, A., Gałkowski, T., Partyka, M. (2023). Convergence of RBF Networks Regression Function Estimates and Classifiers. In: Rutkowski, L., Scherer, R., Korytkowski, M., Pedrycz, W., Tadeusiewicz, R., Zurada, J.M. (eds) Artificial Intelligence and Soft Computing. ICAISC 2022. Lecture Notes in Computer Science(), vol 13588. Springer, Cham. https://doi.org/10.1007/978-3-031-23492-7_31
Download citation
DOI: https://doi.org/10.1007/978-3-031-23492-7_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-23491-0
Online ISBN: 978-3-031-23492-7
eBook Packages: Computer ScienceComputer Science (R0)