Complexity estimates based on integral transforms induced by computational units

  title={Complexity estimates based on integral transforms induced by computational units},
  author={Vera Kurkov{\'a}},
  journal={Neural networks : the official journal of the International Neural Network Society},
Integral transforms with kernels corresponding to computational units are exploited to derive estimates of network complexity. The estimates are obtained by combining tools from nonlinear approximation theory and functional analysis together with representations of functions in the form of infinite neural networks. The results are applied to perceptron networks. 
Highly Cited
This paper has 22 citations. REVIEW CITATIONS

From This Paper

Topics from this paper.


Publications referenced by this paper.
Showing 1-10 of 37 references

Feedforward Neural Network Methodology

Information Science and Statistics • 1999
View 4 Excerpts
Highly Influenced

Dimension-independent rates of approximation by neural networks

V. Kůrková
View 7 Excerpts
Highly Influenced

Neural net approximation

A. R. Barron
Proc. 7th Yale workshop on adaptive and learning systems • 1992
View 9 Excerpts
Highly Influenced

1982).Modern analysis. New York: Dover

A. Friedman
View 6 Excerpts
Highly Influenced

Representations and rates of approximation of real–valued Boolean functions by neural networks

V. Kůrková, P. Savický, K. Hlaváčková
Neural Networks, • 1998
View 1 Excerpt
Highly Influenced

Universal approximation bounds for superpositions of a sigmoidal function

IEEE Trans. Information Theory • 1993
View 6 Excerpts
Highly Influenced

A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training

L. K. Jones
Annals of Statistics, • 1992
View 4 Excerpts
Highly Influenced

Bochner interals and neural networks

P. C. Kainen, A. Vogt
Handbook on neural information processing. Berlin, • 2012
View 1 Excerpt

Similar Papers

Loading similar papers…