Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

December 1, 2001, Vol. 13, No. 12, Pages 2673-2680
(doi: 10.1162/089976601317098484)
© 2001 Massachusetts Institute of Technology
Specification of Training Sets and the Number of Hidden Neurons for Multilayer Perceptrons
Article PDF (79.02 KB)
Abstract

This work concerns the selection of input-output pairs for improved training of multilayer perceptrons, in the context of approximation of univariate real functions. A criterion for the choice of the number of neurons in the hidden layer is also provided. The main idea is based on the fact that Chebyshev polynomials can provide approximations to bounded functions up to a prescribed tolerance, and, in turn, a polynomial of a certain order can be fitted with a three-layer perceptron with a prescribed number of hidden neurons. The results are applied to a sensor identification example.