files/journal/2022-09-02_12-54-44-000000_354.png

Journal of Engineering and Applied Sciences

ISSN: Online 1818-7803
ISSN: Print 1816-949x
105
Views
1
Downloads

Function Approximation by Feed Forward Neural Networks with a Fixed Weights Using Sigmoidal Signals

M. Ramakrishnan , K. Ekamavannan , P. Thangavelu and P. Vivekanandan
Page: 293-297 | Received 21 Sep 2022, Published online: 21 Sep 2022

Full Text Reference XML File PDF File

Abstract

Neural networks have been successfully applied to various pattern recognition and function approximation problems. The author recently introduced left sigmoidal signals and right sigmoidal signals to prove certain function approximation theorems for feed forward neural networks. In this study, by imposing certain conditions on the continuous functions on R, we find those conditions that can be approximated by feed forward neural networks with fixed weights using left sigmoidal signals and right sigmoidal signals.


How to cite this article:

M. Ramakrishnan , K. Ekamavannan , P. Thangavelu and P. Vivekanandan . Function Approximation by Feed Forward Neural Networks with a Fixed Weights Using Sigmoidal Signals.
DOI: https://doi.org/10.36478/jeasci.2006.293.297
URL: https://www.makhillpublications.co/view-article/1816-949x/jeasci.2006.293.297