Complexity Research on Second Class Orthogonal Weight Function Neural Networks

Dai Yuan Zhang; Ran Zhao

doi:10.4028/www.scientific.net/AMR.989-994.2659

Paper Titles

The New Class of Laplacian Integral Graphs
p.2643

An Efficient Methodology for Estimating Interconnect Crosstalk Noise in Deep-Submicron Technologies
p.2647

Feature-Based Real-Time Visual SLAM Using Kinect
p.2651

Research Progress in Topological Relations of Objects with Holes
p.2655

Complexity Research on Second Class Orthogonal Weight Function Neural Networks
p.2659

Research of the First Kind of Padé Weight Function Neural Networks
p.2663

Time Complexity Research on the Second Type Neural Networks of Padé Weight Functions
p.2667

Research on Safety Comprehensive Assessment Method for Air Traffic Control Based on RBF Neural Network
p.2671

On the Application of Ant Colony Neural Network for the Highway Traffic Safety Facilities System
p.2675

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 989-994Complexity Research on Second Class Orthogonal...

Complexity Research on Second Class Orthogonal Weight Function Neural Networks

Abstract:

Weight function neural network is a new kind of neural network developed in recent years, which has many advantages, such as finding globe minima directly, good performance of generalization, extracting some useful information inherent in the problems and so on. Time complexity is an important measure of algorithm. This paper studies the complexity of neural network using second class orthogonal weight functions. The results indicate that the neural network has a linear relationship with the dimensions of input layer and output layer, an O (n³) relationship with the number of samples. Finally gives some simulation experiments for time complexity.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 989-994)

Pages:

2659-2662

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.989-994.2659

Citation:

Cite this paper

Online since:

July 2014

Authors:

Dai Yuan Zhang*, Ran Zhao

Keywords:

Complexity, Neural Network (NN), Orthogonal, Weight Function

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

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

Google Scholar

[2] J. G. Yu, J.E. Lefebvre. Guided waves in multilayered hollow cylinders: The improved Legendre polynomial method[J]. Composite Structures, 2013(95): 419-429.

DOI: 10.1016/j.compstruct.2012.07.012

Google Scholar

[3] Antonio J. Duran, Vanesa Sanchez-Canales. Orthogonal matrix polynomials whose differences are also orthogonal[J]. Journal of Approximation Theory, 2014: 112-127.

DOI: 10.1016/j.jat.2013.11.012

Google Scholar

[4] Caner Ozcan, Baha Sen. Investigation of the performance of LU decomposition method using CUDA [C]. First World Conference on Innovation and Computer Sciences, 2012(1): 50-54.

Google Scholar