Digital Commons Network^™

Characterization Of A Class Of Sigmoid Functions With Applications To Neural Networks, Anil Ravindran Menon, Kishan Mehrotra, Chilukuri K. Mohan, Sanjay Ranka

College of Engineering and Computer Science - Former Departments, Centers, Institutes and Projects

Sigmoid functions, whose graphs are “S-shaped” curves, appear in a great variety of contexts, such as the transfer functions in many neural networks. Their ubiquity is no accident; these curves are among the simplest non-linear curves, striking a graceful balance between linear and non-linear behavior. .. This paper undertakes a study of two classes of sigmoids: the simple sigmoids, defined to be odd, asymptotically bounded, completely monotone functions in one variable, and the Hyperbolic sigmoids, a proper subset of simple sigmoids and a natural generalization of the hyperbolic tangent. The class of hyperbolic sigmoids includes a surprising number of well …