Approximation and Estimation Bounds for Artificial Neural Networks

Machine Learning

Volumn 14, Issue 1, 1994, Pages 115-133

  Barron, Andrew R ^a  

^a YALE UNIVERSITY   (United States)

Author keywords

approximation theory; complexity regularization; estimation theory; Neural nets; statistical risk

Indexed keywords

EID: 0001325515     PISSN: 08856125     EISSN: 15730565     Source Type: Journal    
DOI: 10.1023/A:1022650905902     Document Type: Article

References (29)

1. Statistical properties of artificial neural networks
2. Complexity regularization with applications to artificial neural networks
3. Approximation and estimation bounds for artificial neural networks
4. Universal approximation bounds for superpositions of a sigmoidal function
5. Minimum complexity density estimation
6. Approximation of density functions by sequences of exponential families
7. Approximation of least squares regression on nested subspaces
8. Approximations by superpositions of a sigmoidal function
9. Decision theoretic generalizations of the PAC model for neural net and other learning applications
10. Multi-layer feedforward networks are universal approximators
11. On nonparametric estimation of regression
12. A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
13. L, cross-validation, and generalized cross-validation: discrete index set
14. Nonparametric estimation of smooth regression functions
15. Rate of convergence of nonparametric estimators of maximum-likelihood type
16. k
17. A universal prior for integers and estimation by minimum description length
18. Optimal global rates of convergence for nonparametric estimators
19. Large-sample inference for log-spline models
20. Connectionist nonparametric regression: multilayer feedforward networks can learn arbitrary mappings