Learning-based complexity evaluation of radial basis function networks

Neural Processing Letters

Volumn 16, Issue 2, 2002, Pages 137-150

  Najarian, Kayvan ^a  

^a University of North Carolina at Charlotte   (United States)

Author keywords

Computational complexity; Computational learning theory; Empirical risk minimization algorithm; Radial basis function networks

Indexed keywords

COMPUTATIONAL COMPLEXITY; COMPUTER SIMULATION; FUNCTION EVALUATION; LEARNING ALGORITHMS; LEARNING SYSTEMS; MATHEMATICAL MODELS; OPTIMIZATION; PROBABILITY DISTRIBUTIONS; RISK ASSESSMENT; STATISTICAL METHODS;

COMPLEXITY EVALUATION; COMPUTATIONAL LEARNING THEORY; EMPIRICAL RISK MINIMIZATION ALGORITHM; PROBABLY APPROXIMATELY CORRECT LEARNING THEORY; STATISTICAL CONFIDENCE;

RADIAL BASIS FUNCTION NETWORKS;

EID: 0036784492     PISSN: 13704621     EISSN: None     Source Type: Journal    
DOI: 10.1023/A:1019999408474     Document Type: Article

References (12)

1. A theory of learnable
2. PAC learning in nonlinear FIR models
3. Evolution and optimization '89. Selected papers on evolution theory, combinatorial optimization, and related topics
4. On the uniform convergence of relative frequencies of events to their probabilities
5. The necessary and sufficient conditions of the method of empirical risk minimization
6. A learning-theory-based training algorithm for variable-structure dynamic neural modeling
7. Learning of FIR models under uniform distribution
8. The sample complexity of pattern classification with neural networks: The size of the weights is more important than the size of the network
9. Application of learning theory in neural modeling of dynamic systems
10. Complexity control of neural networks using learning theory, part I: Theory
11. Complexity control of neural networks using learning theory, part II: Applications in neural modelling of two-dimensional scanning system