The hidden layer size in feed-forward neural networks: A statistical point of view

Metron

Volumn 59, Issue 1-2, 2001, Pages 217-227

  Perna, Cira ^a   Giordano, Francesco ^a  

^a UNIVERSITY OF SALERNO   (Italy)

Author keywords

Feed Forward neural networks; Non parametric regression; Smoothing parameter

Indexed keywords

EID: 9944244670     PISSN: 00261424     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (8)

1. Barron, A.R. (1993) Universal Approximation Bounds for Superpositions of a Sigmoidal Function, IEEE Transactions on Information Theory, 39, n. 3, 930-945.
2. Davis, L. (1991) Handbook of Genetic Algorithm, Van Nostrand Reinhold, New-York.
3. Giordano, F and Perna, C. (1998) Proprietà asintotiche degli stimatori neurali nella regressione non parametrica, Atti della XXXIX Riunione Scientifica S.I.S., II, 235-242.
4. Giordano, F and Perna, C. (1999) Large-sample properties of Neural Estimators in a Regression Model with φ-mixing errors, Book of short papers, CLADAG99, 89-92.
5. Haykin, S. (1994) Neural Networks: a comprehensive foundation, Macmillan, New-York.
6. Hornik, K., Stinchcombe, M. and White, H. (1989) Multy-Layer Feedforward Networks Are Universal Approximators, Neural Networks, 2, 359-366.
7. Lachtermacher, G. and Fuller, J.D. (1995) Backpropagation in Time-series Forecasting, J. of Forecasting, 14, 881-393.
8. Lehtokangas, M., Saarinen, J., Huuhtanen, P. and Kaski, K. (1996) Predictive Minimum Description Length Criterion for Time Series Modeling with Neural Networks, Neural Computation, 8, 583-593.