On the Uniform Convergence of the Orthogonal Series-Type Kernel Regression Neural Networks in a Time-Varying Environment

@inproceedings{Er2012OnTU,
  title={On the Uniform Convergence of the Orthogonal Series-Type Kernel Regression Neural Networks in a Time-Varying Environment},
  author={Meng Joo Er and Piotr Duda},
  booktitle={ICAISC},
  year={2012}
}
Sufficient conditions for uniform convergence of general regression neural networks, based on the orthogonal series-type kernel, are given. The convergence is guarantee even if variance of noise diverges to infinity. Simulation results are presented. 

References

SHOWING 1-10 OF 41 REFERENCES
Identification of MISO nonlinear regressions in the presence of a wide class of disturbances
A nonparametric algorithm, based on multiple Fourier series, for identification of MISO (multidimensional-input-single-output) systems is investigated. It is shown that the algorithm converges for a
ORTHOGONAL SERIES ESTIMATES OF A REGRESSION FUNCTION WITH APPLICATIONS IN SYSTEM IDENTIFICATION
Nonparametric estimates of a regression function — based on orthogonal series — are investigated in the case that the domain points are nonrandom. Sufficient conditions for the almost sure
On nonparametric identification with prediction of time-varying systems
Nonparametric procedures-based on the orthogonal series approach-for the real-time identification and prediction of nonstationary systems are presented. It is shown that algorithms are convergent in
On optimal global rate of convergence of some nonparametric identification procedures
A study of orthogonal series procedures for function fitting, motivated by an interest in nonparametric identification of linear dynamic systems, is reported. It is shown that the procedures attain
On-line identification of time-varying systems by nonparametric techniques
A nonparametric algorithm, based on orthogonal series, is proposed for real-time identification of nonstationary systems. It is proved that the algorithm converges in the mean-square sense. The
Real-time identification of time-varying systems by non-parametric algorithms based on Parzen kernels
Non-parametric algorithms, based on Parzen kernels, for the real-time identification of non-stationary systems are presented. Weak and strong pointwise convergence of identification procedures is s...
A fast training algorithm for neural networks
TLDR
The recursive least squares method (RLS) is derived for the learning of multilayer feedforward neural networks and simulation results indicate a fast learning process in comparison to the classical and momentum backpropagation (BP) algorithms.
Nonparametric recovery of multivariate functions with applications to system identification
The methodology for nonparametric fitting of multivariate functions is proposed. The mean-square error convergence and the strong convergence are proved.
Nonparametric fitting of multivariate functions
A nonparametric algorithm, based on the multiple Fejer's sum, for fitting of multivariate functions is proposed. The mean square error convergence and the speed of convergence are investigated.
Multiple Fourier series procedures for extraction of nonlinear regressions from noisy data
TLDR
Three nonparametric procedures for the extraction of nonlinear regressions from noisy data based on the Dirichlet, Fejer, and de la Vallee Poussin multiple kernels are proposed and it is proved that the procedures attain the optimal rate of convergence, which cannot be exceeded by any othernonparametric algorithm.
...
...