عنوان المقالة:لا توجد Training Feed Forward Neural Network with Modified Fletcher-Reeves Method
هشام محمد خضر | Hisham | 8606
نوع النشر
مجلة علمية
المؤلفون بالعربي
ا.د.خليل خضر عبو, ا.م.د.يوكسل عبدالستار صادق, م.م.هشام محمد خضر
المؤلفون بالإنجليزي
Khalil K. Abbo1, Yoksal A. Laylani2, Hisham M. Khudhur3
الملخص العربي
In this research, a modified Fletcher-Reeves (FR) conjugate gradient algorithm for training large scale feed forward neural network (FFNN) is presented. Under mild conditions, we establish that the proposed method satisfies the sufficient descent condition, and it is globally convergent under Wolfe line search condition. The evidence which is provided by experimental results showed that our proposed method is preferable and superior to the classic methods.
تاريخ النشر
01/01/2018
الناشر
Journal of Multidisciplinary Modeling and Optimization
رقم المجلد
1
رقم العدد
2
ISSN/ISBN
2645-923X
رابط DOI
10.13140/RG.2.2.16517.60640
الصفحات
15-22
رابط الملف
تحميل (157 مرات التحميل)
رابط خارجي
https://www.researchgate.net/publication/327339466_Training_Feed_Forward_Neural_Network_with_Modified_Fletcher-Reeves_Method
الكلمات المفتاحية
Unconstrained optimization problem, Conjugate gradient method, Wolfe condition, Globally convergent
رجوع