On the Properties of Error Functions that Affect the Speed of Backpropagation Learning

In the last few years several alternatives to the mean-squared error function have been proposed as a means of improving the speed of backpropagation learning. Perhaps best-known among these are the functions considered in (Fahlman 1988) and the cross-entropy function discussed in (Solla et al., 1988). In this paper we investigate properties of error functions that influence the rate of learning when backpropagation (BP) is employed.