Convergence rates for single hidden layer feedforward networks

Neural Networks

Volumn 7, Issue 1, 1994, Pages 147-158

  McCaffrey, Daniel F ^a   Ronald Gallant, A ^b  

^a RAND CORPORATION   (United States)

^b UNIVERSITY OF NORTH CAROLINA   (United States)

Author keywords

Embedding; Fourier series; Nonparametric regression

Indexed keywords

ESTIMATION; FOURIER TRANSFORMS; LEARNING SYSTEMS; PROBABILITY; REGRESSION ANALYSIS;

CONVERGENCE RATES; HIDDEN LAYER FEEDFORWARD NETWORK;

NEURAL NETWORKS;

EID: 0028320833     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/0893-6080(94)90063-9     Document Type: Article

References (23)

1. Approximation and estimations bounds for artificial neural networks
2. Complexity regularization with application to artificial neural networks
3. On the Tchebychef inequality of Bernstein
4. Approximation by superposition of a sigmoidal function
5. Fourier approximation and embeddings of Sobolev spaces
6. On the approximate realization of continuous mappings by neural networks
7. There exists a neural network that does not make avoidable mistakes
8. On learning the derivatives of an unknown mapping with multilayer feedforward networks
9. Theory of the backpropagation neural network
10. Multilayer feedforward networks are universal approximators
11. Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks
12. A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
13. ε-entropy and ε-capacity of sets in functional spaces
14. Estimating Lyapunov exponents with nonparametric regression and convergence rates for feedforward single hidden layer networks
15. Estimating the Lyapunov exponent of a chaotic system with nonparametric regression
16. Convergence rates of maximum likelihood and related estimation in general parameter spaces
17. Universal approximation using feedforward networks with non-sigmoid hidden layer activation functions
18. Optimal global rates of convergence for nonparametric regression
19. Multilayer feedforward networks can learn arbitrary mappings: Connectionist nonparametric regression with automatic and semi-automatic determination of network complexity