TY  - JOUR
T1  - The Classes of Left and Right sigmoidal signals for Feed forward Neural Networks
AU - , M. Ramakrishnan AU - , C.M. Velu AU - , K. Ekambavanan AU - , P. Thangavelu AU - , P. Vivekanandan 
JO  - International Journal of Soft Computing
VL  - 1
IS  - 2
SP  - 118
EP  - 120
PY  - 2006
DA  - 2001/08/19
SN  - 1816-9503
DO  - ijscomp.2006.118.120
UR  - https://makhillpublications.co/view-article.php?doi=ijscomp.2006.118.120
KW  - Feed forward networks
KW  -activation functions
KW  -sigmoidal signals
KW  -approximation
AB  - The authors recently introduced left sigmoidal signals and right sigmoidal signals to prove certain
function approximation theorems for Feed Forward Neural Networks. In this study we identify a class LS (resp.
RS.) of left sigmoidal (resp.Right sigmoidal) signals having the property that the envelope of the derivatives
of members of a class LS (resp. RS) is a left sigmoidal (resp.Right sigmoidal) signal.
ER  -