Convergence and rates of convergence of radial basis functions networks in function learning

Nonlinear Analysis, Theory, Methods and Applications

Volumn 47, Issue 1, 2001, Pages 281-292

  Krzyak, A ^b   Niemann, H ^a,b  

^a Gina Cody School of Engineering and Computer Science   (Canada)

^b NONE

Author keywords

MISE convergence; Nonlinear regression; Radial basis function networks; Rate of convergence

Indexed keywords

COMPUTATIONAL COMPLEXITY; CONVERGENCE OF NUMERICAL METHODS; ERROR ANALYSIS; PROBLEM SOLVING; RADIAL BASIS FUNCTION NETWORKS; REGRESSION ANALYSIS;

MEAN INTEGRATED SQUARE ERROR (MISE); NONLINEAR FUNCTION LEARNING; NORMALIZED RADIAL BASIS FUNCTION NETWORKS;

LEARNING SYSTEMS;

EID: 0035421744     PISSN: 0362546X     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0362-546X(01)00176-6     Document Type: Article

References (15)

1. Multivariable functional interpolation and adaptive networks
2. Any discrimination rule can have arbitrary bad probability of error for finite sample size
3. 1 convergence of the kernel regression estimate
4. Rates of convergence for radial basis functions and neural networks
5. Regularization theory and neural network architectures
6. Radial basis function networks and complexity regularization in function learning
7. Nonparametric estimation and classification using radial basis function nets and empirical risk minimization
8. Some aspects of radial basis function approximation
9. Fast learning in networks of locally-tuned processing units
10. Universal approximation using radial-basis-function networks
11. Universal approximation using radial-basis-function networks
12. Probabilistic neural networks
13. On radial basis function nets and kernel regression: Statistical consistency, convergence rates and receptive field size