کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
6421487 1631833 2013 12 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
A new conjugate gradient algorithm for training neural networks based on a modified secant equation
ترجمه فارسی عنوان
الگوریتم شبیه سازی جدید برای آموزش شبکه های عصبی بر اساس یک معادله ثابت شده است
موضوعات مرتبط
مهندسی و علوم پایه ریاضیات ریاضیات کاربردی
چکیده انگلیسی

Conjugate gradient methods have been established as excellent neural network training methods, due to the simplicity of their iteration, numerical efficiency and their low memory requirements. In this work, we propose a conjugate gradient neural network training algorithm which guarantees sufficient descent using any line search, avoiding thereby the usually inefficient restarts. Moreover, it approximates the second order curvature information of the error surface with a high-order accuracy by utilizing a new modified secant condition. Under mild conditions, we establish that the global convergence of our proposed method. Experimental results provide evidence that our proposed method is in general superior to the classical conjugate gradient training methods and has a potential to significantly enhance the computational efficiency and robustness of the training process.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Applied Mathematics and Computation - Volume 221, 15 September 2013, Pages 491-502
نویسندگان
, ,