CHEBYSHEV POLYNOMIAL APPROXIMATION FOR ACTIVATION SIGMOID FUNCTION

Miroslav Vlček

《Neural Network World》 22卷4期 (2012/08) Pp. 387-393

https://doi.org/10.14311/NNW.2012.22.023

摘要

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

關鍵字

Sigmoid function ； Chebyshev polynomials ； recursive algorithms