An integral formula for Heaviside neural networks

@inproceedings{Kainen2004AnIF,
  title={An integral formula for Heaviside neural networks},
  author={Paul C. Kainen},
  year={2004}
}
A connection is investigated between integral formulas and neural networks based on the Heaviside function. The integral formula developed by Kůrková, Kainen and Kreinovich is derived in a new way for odd dimensions and extended to even dimensions. In particular, it is shown that well-behaved functions of d variables can be represented by integral combinations of Heavisides with weights depending on higher derivatives. 

From This Paper

Topics from this paper.

References

Publications referenced by this paper.
Showing 1-10 of 15 references

Geometry and topology of continuous best and near best approximations

P. C. Kainen, V. Kůrková, A. Vogt
Journal of Approximation Theory (to appear) • 2000
View 2 Excerpts

Rates of convergence for radial basis function and neural networks

F. Girosi, G. Anzellotti
Artificial Neural Networks for Speech and Vision • 1993

Rates of convergence for radial basis function and neural networks. In Artificial Neural Networks for Speech and Vision (pp. 97–113)

F. Girosi, G. Anzellotti
1993
View 2 Excerpts

Photonic implementations of neural networks, Chap

B. K. Jenkins, A. R. Tanguay, Jr.
Neural Networks for Signal Processing, (Ed. B. Kosko) (pp. 287–382) • 1992
View 1 Excerpt

Construction of neural nets using the radon transform

International 1989 Joint Conference on Neural Networks • 1989
View 2 Excerpts