Global Convergence for Discrete Dynamical Systems and Forward Neural Networks

Authors

ASUMAN G. AKSOY
MARIO MARTELLI

DOI

-

Abstract

Using a theoretical result regarding the global stability of discrete dynamical systems of lower triangular form, we establish convergence properties of forward neural networks when the neuron response functions fail to be continuous.

First Page

345

Last Page

354

Recommended Citation

AKSOY, ASUMAN G. and MARTELLI, MARIO (2001) "Global Convergence for Discrete Dynamical Systems and Forward Neural Networks," Turkish Journal of Mathematics: Vol. 25: No. 2, Article 9. Available at: https://journals.tubitak.gov.tr/math/vol25/iss2/9