Approximation by superpositions of a sigmoidal function

@article{Cybenko1989ApproximationBS,
  title={Approximation by superpositions of a sigmoidal function},
  author={G. Cybenko},
  journal={Mathematics of Control, Signals and Systems},
  year={1989},
  volume={2},
  pages={303-314}
}
  • G. Cybenko
  • Published 1989
  • Mathematics, Computer Science
  • Mathematics of Control, Signals and Systems
  • In this paper we demonstrate that finite linear combinations of compositions of a fixed, univariate function and a set of affine functionals can uniformly approximate any continuous function ofn real variables with support in the unit hypercube; only mild conditions are imposed on the univariate function. Our results settle an open question about representability in the class of single hidden layer neural networks. In particular, we show that arbitrary decision regions can be arbitrarily well… CONTINUE READING
    3,657 Citations

    Tables and Topics from this paper.

    A Single Hidden Layer Feedforward Network with Only One Neuron in the Hidden Layer Can Approximate Any Univariate Function
    • 45
    • PDF
    Approximation properties of a multilayered feedforward artificial neural network
    • H. Mhaskar
    • Mathematics, Computer Science
    • Adv. Comput. Math.
    • 1993
    • 123
    Approximation of functions on a compact set by finite sums of a sigmoid function without scaling
    • Y. Ito
    • Mathematics, Computer Science
    • Neural Networks
    • 1991
    • 113
    • Highly Influenced
    NEURAL NETWORKS FOR OPTIMAL APPROXIMATION OF SMOOTH
    • 7
    Neural Networks for Optimal Approximation of Smooth and Analytic Functions
    • H. Mhaskar
    • Mathematics, Computer Science
    • Neural Computation
    • 1996
    • 245
    • PDF
    Universal Approximation Using Radial-Basis-Function Networks
    • 3,212
    • Highly Influenced
    • PDF
    General approximation theorem on feedforward networks
    • G. Huang, Haroon Atique Babri
    • Mathematics
    • Proceedings of ICICS, 1997 International Conference on Information, Communications and Signal Processing. Theme: Trends in Information Systems Engineering and Wireless Multimedia Communications (Cat.
    • 1997
    • 22
    Approximations of continuous functionals by neural networks with application to dynamic systems
    • T. Chen, H. Chen
    • Mathematics, Computer Science
    • IEEE Trans. Neural Networks
    • 1993
    • 147
    • PDF
    ON APPROXIMATION OF LINEAR FUNCTIONALSON Lp

    References

    SHOWING 1-10 OF 26 REFERENCES
    On the approximate realization of continuous mappings by neural networks
    • 3,997
    • PDF
    Multilayer feedforward networks are universal approximators
    • 14,967
    • PDF
    Construction of neural nets using the radon transform
    • 166
    Classification capabilities of two-layer neural nets
    • 35
    What Size Net Gives Valid Generalization?
    • 1,653
    • PDF
    An introduction to computing with neural nets
    • 3,440
    • PDF
    Neural Net and Traditional Classifiers
    • 171
    • PDF