On the Training of a Kolmogorov Network

  title={On the Training of a Kolmogorov Network},
  author={Mario K{\"o}ppen},
The Kolmogorov theorem gives that the representation of continuous and bounded real-valued functions of n variables by the superposition of functions of one variable and addition is always possible. Based on the fact that each proof of the Kolmogorov theorem or its variants was a constructive one so far, there is the principal possibility to attain such a representation. This paper reviews a procedure for obtaining the Kolmogorov representation of a function, based on an approach given by David… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.


Publications referenced by this paper.
Showing 1-7 of 7 references

Kolmogorov’s theorem and its impact on soft computing

  • H. Nguyen, V. Kreinovich
  • In Yager, R.R., Kacprzyk, J., eds.: The Ordered…
  • 1997
1 Excerpt

Kolmogorov’s mapping neural network existence theorem

  • R. Hecht-Nielsen
  • Proceedings of the First International Conference…
  • 1987
1 Excerpt

On the representation of continuous functions of several variables by superpositions of continuous functions of one variable and addition

  • A. N. Kolmogorov
  • Doklady Akademii Nauk SSSR 114
  • 1957
1 Excerpt

Similar Papers

Loading similar papers…