ICANN ’94 pp 573-576 | Cite as

Cascade Correlation convergence theorem

  • Gian Paolo Drago
  • Sandro Ridella

Abstract

In this paper we prove a theorem which guarantees that the Cascade Correlation algorithm has at least a speed of convergence of order O(1/n h ), where n h is the number of hidden neurons, when approximating a function which is series of sigmoids with a finite number of terms.

Keywords

Covariance 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Barron A.R., IEEE Trans. I. T., vol.39, no.3, May 1993, pp.930–945.Google Scholar
  2. [2]
    Drago G.P. and Ridella S., Proc. of the ICANN’93, pp.750–754.Google Scholar
  3. [3]
    Drago G.P. and Ridella S., submittedGoogle Scholar
  4. [4]
    Fahlman S.E. and Lebiere C., CMU-CS-90–100, February 14, 1990.Google Scholar
  5. [5]
    Jones L.K., Annals of Statistics, vol.20, no. l, 1992, pp.608–613.Google Scholar

Copyright information

© Springer-Verlag London Limited 1994

Authors and Affiliations

  • Gian Paolo Drago
    • 1
  • Sandro Ridella
    • 2
  1. 1.Istituto per i Circuiti Elettronici - CNRGenovaItaly
  2. 2.DIBE - Universita’ di GenovaGenovaItaly

Personalised recommendations