Title :
Low-error approximation of artificial neuron sigmoid function and its derivative
Author :
Armato, A. ; Fanucci, L. ; Pioggia, G. ; De Rossi, D.
Author_Institution :
Interdepartmental Res. Centre E. Piaggio, Pisa, Italy
Abstract :
A new low-error approximation of the sigmoid function based on the piecewise linear method is proposed. The approximation results, in comparison with those of the state-of-the-art, show the lowest mean absolute and relative errors.
Keywords :
approximation theory; neural nets; piecewise linear techniques; artificial neuron sigmoid function; low-error approximation; piecewise linear method;
Journal_Title :
Electronics Letters
DOI :
10.1049/el.2009.1704
