An Improved Training Algorithm for Artificial Neural Networks

Botao Wang, Wu Wei-ling2004

Abstract

In order to resolve the convergence speed problem due to the approximate formula in the process of the recursive least squares back propagation training algorithm(namely RLS-BP), we propose here an improved RLS-BP algorithm, which is deduced through an un-approximation formula. Experiments show that the convergence of the improved algorithm is faster than before. The improved RLS-BP algorithm is more effective.
BibTeX
@misc{wang2004improved,
  author = {Botao Wang and WU Wei-ling},
  title = {{An Improved Training Algorithm for Artificial Neural Networks}},
  year = {2004},
}

Loading related content...

Figure