✨
AI Summary & Key Takeaways
AI Insight⚡ TL;DR(Too Long; Didn't Read)
The evidence which is provided by experimental results showed that our proposed method is preferable and superior to the classic methods.
📌 3 Key Takeaways
🎯
Objective & Hypothesis:In this research, a modified Fletcher-Reeves (FR) conjugate gradient algorithm for training large scale feed forward neural network (FFNN) is presented.
📊
Key Findings & Data:Under mild conditions, we establish that the proposed method satisfies the sufficient descent condition, and it is globally convergent under wolfe line search condition.
💡
Conclusion & Impact:The evidence which is provided by experimental results showed that our proposed method is preferable and superior to the classic methods.
🔬Design:Research Article
📍Scope:Comprehensive Sample
⚙️Variables:Conjugate gradient · Neural network · Global optimization
Abstract
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.
🔖
Cite This Article
LAYLANİ, Y. A., ABBO, K. K., KHUDHUR, H. M. (2018). Training feed forward neural network with modified Fletcher-Reeves method. Journal of Multidisciplinary Modeling and Optimization, Cilt: 1 - Sayı: 1, 14–22. https://ajindex.com/articles/836284