A New Theory of Infinite Series and its Applications in Training Weight Function Neural Networks

Dai Yuan Zhang

doi:10.4028/www.scientific.net/AMM.513-517.679

Paper Titles

Research on the Data Model and the Approaches to Data Mining in the Semi-Structured Data
p.663

Research on Utilization of Library Website Digital Resources Based on Web
p.667

The Elderly Outdoor Sports Monitoring System Based on the Beidou Satellite Navigation System
p.671

Research on the Network Congestion Control Based on GA-PSO Path Optimization
p.675

A New Theory of Infinite Series and its Applications in Training Weight Function Neural Networks
p.679

Chinese Word Segmentation Based on the First Kind of Spline Weight Function Neural Networks
p.683

Implementation of Mail Classification Using Neural Networks of the Second Type Spline Weight Functions
p.687

Research of Generalized Ant Colony Algorithm for Logistics and Distribution
p.691

Short-Term Traffic Flow Forecasting of Road Based on Spline Weight Function Neural Networks
p.695

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 513-517A New Theory of Infinite Series and its...

A New Theory of Infinite Series and its Applications in Training Weight Function Neural Networks

Abstract:

A new theory of infinite series is proposed in this paper, some new important theorems for function expansion and infinite series are also proposed. Unlike Taylors expansion, the expansion generated by a function is not the form of polynomials. In general, the performance of convergence is much better than that obtained by Taylor's Series. The new important theorems lay the foundation for the new theory of infinite series and applications. To describe the performance of the new results obtained in this paper, an example given in this paper shows that the region of convergence is much larger than that of Taylors series. The new infinite series can keep some important properties of original functions. Weight function neural networks are also used to training feedforward neural networks based on the new theory proposed in this paper.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 513-517)

Pages:

679-682

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.513-517.679

Citation:

Cite this paper

Online since:

February 2014

Authors:

Dai Yuan Zhang*

Keywords:

Expansion, Infinite Series, Neural Network (NN), Region of Convergence, Series, Weight Function

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] T. M. Apostal Mathematical Analysis (Pearson Education Asia Limited and China Machine Press, Beijing, ed. 2, 2004), p.113.

Google Scholar

[2] Daiyuan Zhang: New theories and methods on neural networks. Beijing: Tsinghua University Press, 2006 (in Chinese).

Google Scholar

[3] Daiyuan Zhang: Systems Engineering and Electronics (in Chinese). Vol. 28 (2006), p.1434.

Google Scholar

[4] Daiyuan Zhang: Systems Engineering and Electronics (in Chinese). Vol. 30 (2008), p.2274.

Google Scholar

[5] Daiyuan Zhang: In: Proc. 2010 International Conference on Artificial Intelligence and Education, edited by C. Zhao, volume 2, IEEE Press, Hangzhou (2010).

Google Scholar

[6] Daiyuan Zhang: Applied Mechanics and Materials, edited by Y. H. Kim and P. Yarlagadda, Part 2 of Advances in Mechatronics and Control Engineering, Vol. 278-280 (2013), p.1301.

Google Scholar

[7] Daiyuan Zhang: Submitted to Annals of Mathematics (2013).

Google Scholar