Authors : M. Ramakrishnan , C.M. Velu , K. Ekambavanan , P. Thangavelu and P. Vivekanandan
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.
M. Ramakrishnan , C.M. Velu , K. Ekambavanan , P. Thangavelu and P. Vivekanandan , 2006. The Classes of Left and Right sigmoidal signals for Feed forward Neural Networks. International Journal of Soft Computing, 1: 118-120.