On Some Properties of a Hetereogeneous Transfer Function Involving Symmetric Saturated Linear (SATLINS) with Hyperbolic Tangent Sigmoid (TANSIG) Transfer Functions

Abstract

Transfer functions maps the input layer of the statistical neural network model to the output layer.  To do this perfectly, the function must lie within certain bounds.  This is a property of probability distributions.  This paper establishes the heterogeneous transfer function, SATLINS_TANSIG, as a Probability Distribution Functions (p.d.f) by showing that it is proper.  It also shows the mean and variance.