- Journal of Multidisciplinary Modeling and Optimization
- Volume:1 Issue:1
- Training feed forward neural network with modified Fletcher-Reeves method
Training feed forward neural network with modified Fletcher-Reeves method
Authors : Yoksal A LAYLANİ, Khalil K ABBO, Hisham M KHUDHUR
Pages : 14-22
View : 6 | Download : 3
Publication Date : 2018-08-01
Article Type : Research Paper
Abstract :In this research, a modified Fletcher-Reeves insert ignore into journalissuearticles values(FR); conjugate gradient algorithm for training large scale feed forward neural network insert ignore into journalissuearticles values(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.Keywords : Conjugate gradient, Neural network, Global optimization