TY  - JOUR
T1  - Function Approximation by Feed Forward Neural Networks with a Fixed Weights Using Sigmoidal Signals
AU - , M. Ramakrishnan AU - , K. Ekamavannan AU - , P. Thangavelu AU - , P. Vivekanandan 
JO  - Journal of Engineering and Applied Sciences
VL  - 1
IS  - 4
SP  - 293
EP  - 297
PY  - 2006
DA  - 2001/08/19
SN  - 1816-949x
DO  - jeasci.2006.293.297
UR  - https://makhillpublications.co/view-article.php?doi=jeasci.2006.293.297
KW  - Feed forward networks
KW  -approximation
KW  -sigmoidal signals
KW  -activation functions etc
AB  - 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.
ER  -