New ART2/ART2A Algorithm Apply to Entire Real Number Field

Yong Cheng Xu; Yue Li; Guo Ji Shen; Bin Dong

doi:10.4028/www.scientific.net/AMR.834-836.982

Paper Titles

Application of Data Mining in the Forecasting of Railway Passenger Flow
p.958

A Concatenate Code for Error Correcting Code in Bit Pattern Media Recoding System
p.962

The Transceiver Circuit Design of Digital Ultrasonic System
p.968

The Application and Research of CATV Communication Technology in the Field of Electricity Consumption Information Collection in China
p.974

New ART2/ART2A Algorithm Apply to Entire Real Number Field
p.982

Signal Processing of Giant Magnetostritive Force Sensors
p.988

Image Processing Using Discrete Wavelet Transform Based on OMAP3530
p.994

Design of Intelligent Teaching System Based on Data Mining Technology
p.998

A Quick Sorting Algorithm Adaptive to Massive Data with High Repetition Rate
p.1002

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 834-836New ART2/ART2A Algorithm Apply to Entire Real...

New ART2/ART2A Algorithm Apply to Entire Real Number Field

Abstract:

In this paper, two shortcomings of standard ART2/ART2A algorithm were revealed through theoretical analysis: (1)Standard ART2/ART2A algorithm is only suitable for the case in the nonnegative real number field because of a limit of pretreating process in F₁ layer; (2)Even through all input patterns are shifted to the nonnegative real number field through coordinate transformation, the standard ART2/ART2A algorithm can not correctly recognize those patterns which have same phase, but different amplitudes. As a result, the standard ART2/ART2A algorithm is not quite suitable for universal pattern recognition. So this paper presented a new nonlinear transforming function in F₁layer and a new competitive learning formula in F₂ layer for traditional ART2/ART2A algorithm. The applicable scope of the new ART2/ART2A algorithm is expanded to entire real number field from nonnegative real number field. The result of typical calculation example shows that the presented algorithm is effective.

You might also be interested in these eBooks

Research in Materials and Manufacturing Technologies

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 834-836)

Pages:

982-987

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.834-836.982

Citation:

Cite this paper

Online since:

October 2013

Authors:

Yong Cheng Xu*, Yue Li, Guo Ji Shen, Bin Dong

Keywords:

Adaptive Resonance Theory, ART2, ART2A, Neural Network (NN), Pattern Recognition

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Gail A. Carpenter , Stephen Grossberg. Applied Optics, 1987, 26(23): 4919~4930.

Google Scholar

[2] Carpenter, G.A., Grossberg S. Neural Networks, 1990, (3): 129~152.

Google Scholar

[3] Maartje E.J. Raijmakers Peter C.M. Molenaar. Neural Networks, 1997, 10(4): 649~669.

Google Scholar

[4] Whiteley J.R., Davis J.F., Mehrotra A., Ahalt S.C. IEEE Trans. on Systems, Man and Cybernetics, 1996 , 26(4): 423~437.

DOI: 10.1109/3468.508821

Google Scholar

[5] Filippidis, A.; Jain, L.C.; Lozo, P. IEEE Transactions on Neural Networks, 1999, 1: 186~193.

Google Scholar

[6] Serrano-Gotarredona T, Linares-Barranco B. IEEE Trans. On Neural Networks, 1997, 8(5): 1184~1194.

Google Scholar

[7] Yaghini, Masoud, Shadmani Mohammad Ali. Artificial Intelligence Review, 2013, 39(3): 183~193.

Google Scholar