Approximation properties of a multilayered feedforward artificial neural network

@article{Mhaskar1993ApproximationPO,
  title={Approximation properties of a multilayered feedforward artificial neural network},
  author={Hrushikesh Narhar Mhaskar},
  journal={Adv. Comput. Math.},
  year={1993},
  volume={1},
  pages={61-80}
}
We prove that an artificial neural network with multiple hidden layers and a kthorder sigmoidal response function can be used to approximate any continuous function on any compact subset of a Euclidean space so as to achieve the Jackson rate of approximation. Moreover, if the function to be approximated has an analytic extension, then a nearly geometric rate of approximation can be achieved. We also discuss the problem of approximation of a compact subset of a Euclidean space with such networks… CONTINUE READING

From This Paper

Topics from this paper.

Citations

Publications citing this paper.
Showing 1-10 of 45 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 22 references

On some ext~emeal functions and their applications in the theory of analytic functions of several complex variables

  • J. Siciak
  • Trans. Amer. Math. Soc. 105
  • 1962
Highly Influential
3 Excerpts

Realization of neural networks with one hidden layer

  • C. K. Chui, X. Li
  • CAT Report No. 244, Texas A&M University
  • 1991
2 Excerpts

A constructive proof of approximation by superpositiun of sigmoidal functions for neural networks

  • T. P. Chen, H. Chen, R. W. Liu
  • Preprint
  • 1990
2 Excerpts

Direct and converse theorems for spline approximation with free knots , Bulg

  • V. A. Popov
  • Math . Publ .
  • 1990

Similar Papers

Loading similar papers…