Title :
Approximation of continuous functions defined on a curve by feed-forward neural networks
Author :
Zhou, Zhenghua ; Wan, Wanggen ; Zhou, Xueli
Author_Institution :
Sch. of Commun. & Inf. Eng., Shanghai Univ., Shanghai, China
Abstract :
It´s an important problem in computer aided geometry design to approximate continuous functions defined on a smooth curve, which is widely applied in industry and engineering. In this paper, we approximate continuous functions defined on a smooth single-value curve by means of a new and popular tool- single-hidden layer feed-forward neural networks. It´s checked that the approximation is simple, quick and can be easily realized by the Matlab.
Keywords :
computational geometry; feedforward neural nets; function approximation; mathematics computing; Matlab; computer aided geometry design; continuous function approximation; feedforward neural networks; popular tool- single-hidden layer; smooth single-value curve; Artificial neural networks; Computers; Interpolation; Neurons; Polynomials; Spline;
Conference_Titel :
Natural Computation (ICNC), 2010 Sixth International Conference on
Print_ISBN :
978-1-4244-5958-2
DOI :
10.1109/ICNC.2010.5583710
