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.
Low-error approximation of artificial neuron sigmoid function and its derivative
FANUCCI, LUCA;PIOGGIA, GIOVANNI;DE ROSSI, DANILO EMILIO
2009-01-01
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.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
