Back to Search
Start Over
An improved training algorithm for feedforward neural network learning based on terminal attractors.
- Source :
- Journal of Global Optimization; Oct2011, Vol. 51 Issue 2, p271-284, 14p
- Publication Year :
- 2011
-
Abstract
- In this paper, an improved training algorithm based on the terminal attractor concept for feedforward neural network learning is proposed. A condition to avoid the singularity problem is proposed. The effectiveness of the proposed algorithm is evaluated by various simulation results for a function approximation problem and a stock market index prediction problem. It is shown that the terminal attractor based training algorithm performs consistently in comparison with other existing training algorithms. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 09255001
- Volume :
- 51
- Issue :
- 2
- Database :
- Complementary Index
- Journal :
- Journal of Global Optimization
- Publication Type :
- Academic Journal
- Accession number :
- 65042090
- Full Text :
- https://doi.org/10.1007/s10898-010-9597-6