Approximation of curves contained on the surface by freed-forward neural networks

Authors:
Zhenghua Zhou;Jianwei Zhao
Affiliations:
Department of information and mathematics Sciences, China Jiliang University, Hangzhou, China;Department of information and mathematics Sciences, China Jiliang University, Hangzhou, China
Venue:
AICI'11 Proceedings of the Third international conference on Artificial intelligence and computational intelligence - Volume Part III
Year:
2011

Citing 6
Cited 0

Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks

Neural Networks
Original Contribution: Multilayer feedforward networks with a nonpolynomial activation function can approximate any function

Neural Networks
Original Contribution: On the complexity of approximating mappings using feedforward networks

Neural Networks
Spherical splines and orientation interpolation

The Visual Computer: International Journal of Computer Graphics
On simultaneous approximations by radial basis function neural networks

Applied Mathematics and Computation
The estimate for approximation error of neural networks: A constructive approach

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Based on Freed-forward Neural Networks, we develop a new method to approximate curves contained on the given surface; the main contribution is to convert the problems of space curve approximation on surfaces into the plane curve approximation by point projection. The final approximation curve restricted on the surface is achieved via the intersection of surface and cylinder whose directrix is plane approximation curve by freed-forword Neural Networks method, we also give an upper bound estimation about approximation accuracy.The experiment results show that the method achieve good effect compared to traditional methods nusing piecewise function to represent the curve on the surface.