There exists a neural network that does not make avoidable mistakes

@article{Gallant1988ThereEA,
  title={There exists a neural network that does not make avoidable mistakes},
  author={A. Ronald Gallant and Halbert White},
  journal={IEEE 1988 International Conference on Neural Networks},
  year={1988},
  pages={657-664 vol.1}
}
The authors show that a multiple-input, single-output, single-hidden-layer feedforward network with (known) hardwired connections from input to hidden layer, monotone squashing at the hidden layer and no squashing at the output embeds as a special case a so-called Fourier network, which yields a Fourier series approximation properties of Fourier series representations. In particular, approximation to any desired accuracy of any square integrable function can be achieved by such a network, using… CONTINUE READING
Highly Influential
This paper has highly influenced 12 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS

From This Paper

Topics from this paper.

Citations

Publications citing this paper.
Showing 1-10 of 83 extracted citations

References

Publications referenced by this paper.
Showing 1-4 of 4 references

1987b]: "Some Asymptotic Results for Learning in Single Hidden Layer Feedforward Network Models,1' UCSD Department of Economics Discussion Paper 87113

  • H. White
  • 1987

Kolmogorov's Mapping Neural Network Existence Theorem,

  • R. Hecht-Nielsen
  • IEEE First International Conference on Neural…
  • 1987
1 Excerpt

The Thirteenth Problem of Hilbert

  • G. G. Lorenz
  • Proceedings of Symposia in Pure Mathematics,
  • 1976

" On the Representation of Continuous Functions of Many Variables by Superposition of Continuous Functions of One Variable and Addition

  • A. N. Kolmogorov
  • IEEE First International Conference on Neural…

Similar Papers

Loading similar papers…