Adaptive Error Constrained Backpropagation Algorithm 


Vol. 28,  No. 10, pp. 1007-1012, Oct.  2003


PDF
  Abstract

In order to accelerate the convergence speed of the conventional BP algorithm, constrained optimization techniques are applied to the BP algorithm. First, the noise-constrained least mean square algorithm and the zero noise-constrained LMS algorithm arc applied (designated the NCBP and ZNCBP algorithms, respectively). These methods involve an important assumption: the filter or the receiver in the NCBP algorithm must know the noise variance. By means of extension and generalization of these algorithms, the authors derive an adaptive error-constrained BP algorithm, in which the error variance is estimated. This is achieved by modifying the error function of the conventional BP algorithm using Lagrangian multipliers. The convergence speeds of the proposed algorithms are 20 to 30 times faster than those of the conventional BP algorithm, and are faster than or almost the same as that achieved with a conventional linear adaptive filter using an LMS algorithm.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

S. Choi, K. Ko, D. Hong, "Adaptive Error Constrained Backpropagation Algorithm," The Journal of Korean Institute of Communications and Information Sciences, vol. 28, no. 10, pp. 1007-1012, 2003. DOI: .

[ACM Style]

Soo-Yong Choi, Kyun-Byoung Ko, and Dae-Sik Hong. 2003. Adaptive Error Constrained Backpropagation Algorithm. The Journal of Korean Institute of Communications and Information Sciences, 28, 10, (2003), 1007-1012. DOI: .

[KICS Style]

Soo-Yong Choi, Kyun-Byoung Ko, Dae-Sik Hong, "Adaptive Error Constrained Backpropagation Algorithm," The Journal of Korean Institute of Communications and Information Sciences, vol. 28, no. 10, pp. 1007-1012, 10. 2003.

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880