Approximation Analysis for a New Kind of Neural Network Using Rational Spline Weight Functions

Dai Yuan Zhang; Shan Jiang Hou

doi:10.4028/www.scientific.net/AMM.644-650.1654

Paper Titles

Study on Model for Structural Reliability Based on Dynamic Interfering Theory
p.1633

A Novel Twin Support Vector Machines with Manifold Regularization
p.1640

The Special Form of Second Order Accuracy N-S Equations for Incompressible Fluid
p.1644

The Algebraic Algorithm for Solving the Path Planning Problem of a Weighted Directed Graph
p.1648

Approximation Analysis for a New Kind of Neural Network Using Rational Spline Weight Functions
p.1654

Complexity Analysis of Neural Network Based on Rational Spline Weight Functions
p.1658

A Clutter Suppression Algorithm for GPR Data Based on PCA Combining with Gradient Magnitude
p.1662

Construction of Asymmetric Quantum Product Codes Based Repeated-Root Cyclic Codes
p.1668

Study on Reconstruction Property of Revolved Surface Based on B-Spline
p.1674

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 644-650Approximation Analysis for a New Kind of Neural...

Approximation Analysis for a New Kind of Neural Network Using Rational Spline Weight Functions

Abstract:

To describe the performance for a new kind of neural network, This paper discusses the approximation of the neural network using a kind of rational spline weight function. The rational spline consists of piecewise rational functions with cubic numerators and linear denominators. The theoretic formula of approximation is proposed and an example is also given. It can be concluded that this new neural network can get very high training accuracy.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 644-650)

Pages:

1654-1657

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.644-650.1654

Citation:

Cite this paper

Online since:

September 2014

Authors:

Dai Yuan Zhang*, Shan Jiang Hou

Keywords:

Approximation, Neural Network (NN), Rational Interpolation, Spline Weight Function

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Daiyuan Zhang. New Theories and Methods on Neural Networks[M]. Beijing: Tsinghua University Press, (2006).

Google Scholar

[2] Yan Wang, Jieqing Tan, Zhiming Li, Tian Bai. Weighted Rational Quartic Spline Interpolation[J]. Information & Computational Science, 2013, 10(9): 2651-2658.

DOI: 10.12733/jics20101820

Google Scholar

[3] Duan Qi, K. Djidjeli, W.G. Price, E.H. Twizell, Weighted rational cubic spline interpolation and its application[J]. Journal of computational and Applied Mathmatics, 2000, 2(117): 121-1356.

DOI: 10.1016/s0377-0427(99)00336-2

Google Scholar

[4] Meng Tian, Qiuju Bian. A rational cubic spline interpolation and its application [J], Digital Manufacturing & Automation. 2010(1): 97-99.

DOI: 10.1109/icdma.2010.90

Google Scholar

[5] Xingang Wang. Error Analysis of the Derivative of the Rational Interpolation Based on Function Values[J]. Multimedia and Signal Processing. 2011(2): 198-201.

Google Scholar

[6] Maria Hussain, Sidra Saleem. C1 rational quadratic trigonometric spline[J], Egyptian Informatics Journal. 2013(2): 211-220.

DOI: 10.1016/j.eij.2013.09.002

Google Scholar