M. Ramakrishnan  , C.M. Velu  , K. Ekambavanan  , P. Thangavelu  , P. Vivekanandan  , 
    The Classes of Left and Right sigmoidal signals for Feed forward Neural Networks,
    International Journal of Soft Computing,
    Volume 1,Issue 2,
    2006,
    Pages 118-120,
    ISSN 1816-9503,
    ijscomp.2006.118.120,
    (https://makhillpublications.co/view-article.php?doi=ijscomp.2006.118.120)
    Abstract: 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.
    Keywords: Feed forward networks;activation functions;sigmoidal signals;approximation