Multilayer feedforward networks are universal approximators

@article{Hornik1989MultilayerFN,
  title={Multilayer feedforward networks are universal approximators},
  author={K. Hornik and M. Stinchcombe and H. White},
  journal={Neural Networks},
  year={1989},
  volume={2},
  pages={359-366}
}
  • K. Hornik, M. Stinchcombe, H. White
  • Published 1989
  • Mathematics, Computer Science
  • Neural Networks
  • Abstract This paper rigorously establishes that standard multilayer feedforward networks with as few as one hidden layer using arbitrary squashing functions are capable of approximating any Borel measurable function from one finite dimensional space to another to any desired degree of accuracy, provided sufficiently many hidden units are available. In this sense, multilayer feedforward networks are a class of universal approximators. 
    15,287 Citations

    Topics from this paper

    Approximation capabilities of multilayer feedforward networks
    • K. Hornik
    • Mathematics, Computer Science
    • Neural Networks
    • 1991
    • 3,863
    • PDF
    Neural networks for localized approximation
    • 83
    • PDF
    A constructive method for multivariate function approximation by multilayer perceptrons
    • 100
    Constructive Approximation of Discontinuous Functions by Neural Networks
    • 19
    Function approximation using a partition of the input space
    • P. Koiran
    • Mathematics
    • [Proceedings 1992] IJCNN International Joint Conference on Neural Networks
    • 1992
    Generalization and Approximation Capabilities of Multilayer Networks
    • Y. Takahashi
    • Mathematics, Computer Science
    • Neural Computation
    • 1993
    • 16
    NEURAL NETWORKS FOR OPTIMAL APPROXIMATION OF SMOOTH
    • 7

    References

    SHOWING 1-10 OF 24 REFERENCES
    Universal approximation using feedforward networks with non-sigmoid hidden layer activation functions
    • 269
    • PDF
    There exists a neural network that does not make avoidable mistakes
    • A. Gallant, H. White
    • Mathematics, Computer Science
    • IEEE 1988 International Conference on Neural Networks
    • 1988
    • 194
    Approximation by superpositions of a sigmoidal function
    • G. Cybenko
    • Mathematics, Computer Science
    • Math. Control. Signals Syst.
    • 1989
    • 4,036
    • PDF
    Nonlinear dynamics of artificial neural systems
    • 60
    Principles of mathematical analysis
    • 5,987
    • PDF
    Theory of the Back Propagation Neural Network
    • 505
    Approximation by superpositions of a sigmoidaifunction
    • Urbana
    • 1988
    Capabilities of three layer percep - trans
    • IEEE Second International Conference on Neural Networks
    • 1988
    Multilayer feedforward networks are universal approximators (Discussion Paper 88-45)
    • Multilayer feedforward networks are universal approximators (Discussion Paper 88-45)
    • 1988