论文信息 - Low-error approximation of artificial neuron sigmoid function and its derivative - 字舞流文

Low-error approximation of artificial neuron sigmoid function and its derivative

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.

Luca Fanucci | D. De Rossi | Giovanni Pioggia | Antonino Armato | D. Rossi | G. Pioggia | L. Fanucci | A. Armato

[1] Stamatis Vassiliadis,et al. Sigmoid Generators for Neural Computing Using Piecewise Approximations , 1996, IEEE Trans. Computers.

[2] J. M. Tarela,et al. Digital design of sigmoid approximator for artificial neural networks , 2002 .

[3] Matti Tommiska,et al. Efficient digital implementation of the sigmoid function for reprogrammable logic , 2003 .

[4] C. Alippi,et al. Simple approximation of sigmoidal functions: realistic design of digital neural networks capable of learning , 1991, 1991., IEEE International Sympoisum on Circuits and Systems.

[5] D. J. Myers,et al. Efficient implementation of piecewise linear activation function for digital VLSI neural networks , 1989 .

[6] Mariusz Bajger,et al. Low-error, High-speed Approximation of the Sigmoid Function for Large FPGA Implementations , 2008, J. Signal Process. Syst..