|
|
New Scaled Conjugate Gradient Algorithm For Training Artificial Neural Networks Based on Pure Conjugacy Condition
|
|
|
|
|
نویسنده
|
Abbo Khalil K. ,Mohamed Hind H.
|
منبع
|
Kirkuk University Journal: Scientific Studies - 2015 - دوره : 10 - شماره : 3 - صفحه:230 -241
|
|
|
چکیده
|
Conjugate gradient methods constitute excellent neural network training methods characterized by their simplicity efficiency and their very low memory requirements. in this paper, we propose a new scaled conjugate gradient neural network training algorithm which guarantees descent property with standard wolfe condition. encouraging numerical experiments verify that the proposed algorithm provides fast and stable convergence.
|
کلیدواژه
|
Feed-Forward Neural Networks ,Training Algorithms
|
آدرس
|
Mosul University, College Of Computer Science & Mathematics, Department Of Mathematics, Iraq, University Of Mosul, College Of Computer Sci And Math, Department Of Math, Iraq
|
پست الکترونیکی
|
hinm@yahoo.com
|
|
|
|
|
|
|
|
|
|
|
|
Authors
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|