Testing Error Estimates for Regularization and Radial Function Networks | SpringerLink
Skip to main content
Springer Nature Link
Log in

Testing Error Estimates for Regularization and Radial Function Networks

  • Conference paper
Advances in Neural Networks - ISNN 2008 (ISNN 2008)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 5263))

Included in the following conference series:

Abstract

Regularization theory presents a sound framework to solving supervised learning problems. However, there is a gap between the theoretical results and practical suitability of regularization networks (RN). Radial basis function networks (RBF) can be seen as a special case of regularization networks with a selection of learning algorithms. We study a relationship between RN and RBF, and experimentally evaluate their approximation and generalization ability with respect to number of hidden units.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Haykin, S.: Neural Networks: A Comprehensive Foundation, 2nd edn. Tom Robins (1999)

    Google Scholar 

  2. Xu, L., Krzyżak, A., Yuille, A.: On Radial Basis Function Nets and Kernel Regression: Statistical Consistency, Convergence Rates, and Receptive Field Size. Neural Netw. 7(4), 609–628 (1994)

    Article  MATH  Google Scholar 

  3. Corradi, V., White, H.: Regularized Neural Networks: Some Convergence Rate Results. Neural Computation 7, 1225–1244 (1995)

    Article  Google Scholar 

  4. Kuková, V., Sanguineti, M.: Learning with Generalization Capability by Kernal Methods of Bounded Complexity. J. Complex 21(3), 350–367 (2005)

    Article  Google Scholar 

  5. Tikhonov, A., Arsenin, V.: Solutions of Ill-posed Problems. W.H. Winston, Washington (1977)

    MATH  Google Scholar 

  6. Poggio, T., Girosi, F.: A Theory of Networks for Approximation and Learning. Technical report, Cambridge, MA, USA (1989)

    Google Scholar 

  7. Poggio, T., Smale, S.: The Mathematics of Learning: Dealing with Data. Notices of the AMS 50, 536–544 (2003)

    MathSciNet  Google Scholar 

  8. Powel, M.: Radial Basis Functions for Multivariable Interpolation: A review. In: IMA Conference on Algorithms for the Approximation of Functions and Data, RMCS, Shrivenham, England, pp. 143–167 (1985)

    Google Scholar 

  9. Neruda, R., Kudová, P.: Learning Methods for Radial Basis Functions Networks. Future Generation Computer Systems 21, 1131–1142 (2005)

    Article  Google Scholar 

  10. Prechelt, L.: PROBEN1 – A Set of Benchmarks and Benchmarking Rules for Neural Network Training Algorithms. Technical Report 21/94, Universitaet Karlsruhe (1994)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institute of Computer Science, Academy of Sciences of the Czech Republic, Pod vodárenskou věží 2, Prague, 8, Czech Republic

    Petra Vidnerová & Roman Neruda

Authors
  1. Petra Vidnerová
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Roman Neruda
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Department of Computer Science and Technology, Tsinghu University, 100084, Beijing, China

    Fuchun Sun

  2. Institute TAMS (Technical Aspects of Multimodal Systems), department of Informatics, University of Hamburg, Vogt-Koelln-Straße 30, 22527, Hamburg, Germany

    Jianwei Zhang

  3. Intel China Research Center, 8/F, Peking University, Department of Machine Intelligence, 100871, Beijing, China

    Ying Tan

  4. Department of Mathematics, Southeast University, 210096, Nanjing, China

    Jinde Cao

  5. Departamento de Control Automático, CINVESTAV-IPN, A.P. 14-740, Av.IPN 2508, 07360, México D.F., México

    Wen Yu

Rights and permissions

Reprints and permissions

Copyright information

© 2008 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Vidnerová, P., Neruda, R. (2008). Testing Error Estimates for Regularization and Radial Function Networks. In: Sun, F., Zhang, J., Tan, Y., Cao, J., Yu, W. (eds) Advances in Neural Networks - ISNN 2008. ISNN 2008. Lecture Notes in Computer Science, vol 5263. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-87732-5_61

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-87732-5_61

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-87731-8

  • Online ISBN: 978-3-540-87732-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics