Improved Three-term Conjugate Gradient Algorithm For Training Neural Network
A new three-term conjugate gradient algorithm for training feed-forward neural networks is developed. It is a vector based training algorithm derived from DFP quasi-Newton and has only O(n) memory. The global convergence to the proposed algorithm has been established for convex function under W...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Faculty of Computer Science and Mathematics, University of Kufa
2015-06-01
|
| Series: | Journal of Kufa for Mathematics and Computer |
| Subjects: | |
| Online Access: | https://journal.uokufa.edu.iq/index.php/jkmc/article/view/2137 |
| Summary: | A new three-term conjugate gradient algorithm for training feed-forward neural networks is developed. It is a vector based training algorithm derived from DFP quasi-Newton and has only O(n) memory. The global convergence to the proposed algorithm has been established for convex function under Wolfe condition. The results of numerical experiments are included and compared with other well known training algorithms in this field. |
|---|---|
| ISSN: | 2076-1171 2518-0010 |