Radial basis function networks and complexity regularization in function learning

@article{Krzyak1996RadialBF,
  title={Radial basis function networks and complexity regularization in function learning},
  author={Adam Krzyżak and Tam{\'a}s Linder},
  journal={IEEE transactions on neural networks},
  year={1996},
  volume={9 2},
  pages={
          247-56
        }
}
In this paper we apply the method of complexity regularization to derive estimation bounds for nonlinear function estimation using a single hidden layer radial basis function network. Our approach differs from previous complexity regularization neural-network function learning schemes in that we operate with random covering numbers and l(1) metric entropy, making it possible to consider much broader families of activation functions, namely functions of bounded variation. Some constraints… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 49 CITATIONS

Approximation and estimation bounds for free knot splines

  • Computers & Mathematics with Applications
  • 2013
VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Generalization Performance of Radial Basis Function Networks

  • IEEE Transactions on Neural Networks and Learning Systems
  • 2015
VIEW 18 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Optimum steepest descent higher level learning radial basis function network

VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Artificial Intelligence and Soft Computing

  • Lecture Notes in Computer Science
  • 2013
VIEW 10 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Universal learning using free multivariate splines

  • Neurocomputing
  • 2013
VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Nonparametric regression estimation by normalized radial basis function networks

  • IEEE Transactions on Information Theory
  • 2003
VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Radial Basis Function Networks with optimal kernels

  • 2011 IEEE International Symposium on Information Theory Proceedings
  • 2011
VIEW 5 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Learning Pattern Classification - A Survey

  • IEEE Trans. Information Theory
  • 1998
VIEW 5 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Radial basis function networks in nonparametric classification and function learning

  • Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170)
  • 1998
VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

References

Publications referenced by this paper.
SHOWING 1-10 OF 30 REFERENCES

Strong universal consistency of neural network classifiers

  • IEEE Trans. Information Theory
  • 1993
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Similar Papers

Loading similar papers…