论文信息 - CHEBYSHEV POLYNOMIAL APPROXIMATION FOR ACTIVATION SIGMOID FUNCTION

CHEBYSHEV POLYNOMIAL APPROXIMATION FOR ACTIVATION SIGMOID FUNCTION

An alternative polynomial approximation for the activation sigmoid function is developed here. It can considerably simplify the input/output opera- tions of a neural network. The recursive algorithm is found for Chebyshev expan- sion of all constituting polynomials.

M. Vlcek

[1] G. Meinardus. Approximation von Funktionen und ihre numerische Behandlung , 1964 .

[2] Tsu-Tian Lee,et al. The Chebyshev-polynomials-based unified model neural networks for function approximation , 1998, IEEE Trans. Syst. Man Cybern. Part B.

[3] Norbert Jankowski,et al. Survey of Neural Transfer Functions , 1999 .

[4] Pavel Zahradnik,et al. Analytical design of FIR filters , 1999, ICECS'99. Proceedings of ICECS '99. 6th IEEE International Conference on Electronics, Circuits and Systems (Cat. No.99EX357).

[5] Pavel Zahradnik,et al. Analytical design of FIR filters , 2000, IEEE Trans. Signal Process..

[6] J. M. Tarela,et al. Approximation of sigmoid function and the derivative for hardware implementation of artificial neurons , 2004 .

[7] Luca Fanucci,et al. Low-error approximation of artificial neuron sigmoid function and its derivative , 2009 .