Connectionist nonparametric regression: Multilayer feedforward networks can learn arbitrary mappings

Neural Networks

Volumn 3, Issue 5, 1990, Pages 535-549

  White, Halbert ^a  

^a UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

Convergence; Feedforward networks; Learning; Nonparametric; Regression

Indexed keywords

LEARNING SYSTEMS;

CONNECTIONIST NONPARAMETRIC REGRESSION; FEEDFORWARD NETWORKS; MULTILAYER FEEDFORWARD NETWORKS; NETWORK APPROXIMATION ERROR; NETWORK COMPLEXITY;

NEURAL NETWORKS;

EID: 0025635525     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/0893-6080(90)90004-5     Document Type: Article

References (35)

1. Asymptotic normality of series estimators for various nonparametric and semi-parametric estimators
2. A new approach for finding the global minimum of error function of neural networks
3. Statistical properties of artificial neural networks
4. Kernel estimators of regression functions
5. Inégalité de Bernstein pour les processus stationnaires et mélangeants. Applications
6. Construction of neural nets using the radon transform
7. Multivariate smoothing splines
8. Approximation by superpositions of a sigmoid function
9. On the approximate realization of continuous mappings by neural networks
10. Seminonparametric maximum likelihood estimation
11. Nonparametric maximum likelihood estimation by the method of sieves
12. Generalizing the PAC model for neural net and other learning applications
13. Theory of the backpropagation neural network
14. Multilayer feedforward networks are universal approximators
15. Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks
16. ε-entropy and ε-capacity of sets in functional spaces
17. L, cross-validation and generalized cross validation: Discrete index set
18. Learning internal representations by error propagation
19. Universal approximation using feedforward networks with non-sigmoid hidden layer activation functions
20. Some measurability results for extrema of random functions over random sets
21. Cross-validitory choice and assessment of statistical predictions
22. On the uniform convergence of relative frequencies of events to their probabilities
23. Smoothing noisy data with spline functions
24. A completely automatic French curve: Fitting spline functions by cross validation
25. Learning in artificial neural networks A statistical perspective
26. A practical cross-validation method for multilayer feedforward networks
27. Some results on sieve estimation with dependent observations