- All Journals
- Al-Qadisiyah University
- Basrah University
- Kirkuk University
- Mosul University
- The Iraqi Borad for Medical Specialization
- University of Anbar
- University of Technology
- Al Mustafa University
- Al-Zahraa University for Women
- Alnoor University
- Kunooz University
- Misan University
- Ninevah University
- Tikrit University
- University of Al-Hamdaniya
- University of Kerbala
Conjugate Gradient Algorithm as Improvement Neural Network | ||
| Tikrit Journal of Pure Science | ||
| Article 1, Volume 17, Issue 4, 2012, Pages 249-256 | ||
| Authors | ||
| Nidhal H. al-Assady; Shatha A. M | ||
| Abstract | ||
| Artificial neural networks are once applications of artificial intelligence; in this paper devised delta learning rule by using the behavior of conjugate gradient algorithm (which consider once of traditional methods for solving nonlinear optimization problems), depending on a appropriate learning ratio(c).Finally, a neural network with high speed and of a supervised type was obtained, in general this mathematical style proposed as a neural network proved to be efficient with regard the results for different letters, comparing with results of standard delta rule. | ||
| Keywords | ||
| Artificial Neural Network; conjugate gradient algorithm; delta learning rule; rule; English letters | ||
|
Statistics Article View: 168 PDF Download: 139 |
||