Optimization of a network with Gaussian kernel functions based on the estimation of error confidence intervals

Proceedings of the International Joint Conference on Neural Networks

Volumn 3, Issue , 2001, Pages 1762-1766

  Kil, R M ^a   Koo, I ^a  

^a Korea Advanced Institute of Science and Technology (KAIST)   (South Korea)

Author keywords

[No Author keywords available]

Indexed keywords

APPROXIMATION THEORY; DIFFERENTIAL EQUATIONS; ERRORS; ESTIMATION; FUNCTIONS; LEARNING SYSTEMS; OPTIMIZATION; THEOREM PROVING;

ERROR CONFIDENCE INTERVALS; GAUSSIAN KERNEL FUNCTIOS; MACKEY-GLASS CHAOTIC TIME SERIES; PROBABLY APPROXIMATELY CORRECT LEARNING;

NEURAL NETWORKS;

EID: 0034877898     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (9)

1. A theory of learnability
2. Decision theoretic generalizations of the pac model for neural net and other learning applications
3. On the relationship between generalization error, hypothesis complexity, and sample complexity for radial basis functions
4. Structural optimization of radial basis function networks for function approximation
5. Function approximation based on a network with kernel functions of bounds and locality: An approach of non-parametric estimation
6. Radial basis functions for multivariable interpolation: A review. In J. Mason and M. Cox, Editors
7. A gaussian potential function network with hierarchically self-organizing learning
8. The necessary and sufficient conditions for consistency of the method of risk minimization