آمار

تعداد نشریات27
تعداد شماره‌ها366
تعداد مقالات3,242
تعداد مشاهده مقاله4,756,192
تعداد دریافت فایل اصل مقاله3,246,082
Jafarian, Ahamad, Measoomy Nia, Safa. (1392). Using feed-back neural network method for solving linear fredholm integral equations of the second kind. سامانه مدیریت نشریات علمی, 2(1), 53-71. doi: 10.22098/jhs.2013.2555
Ahamad Jafarian; Safa Measoomy Nia. "Using feed-back neural network method for solving linear fredholm integral equations of the second kind". سامانه مدیریت نشریات علمی, 2, 1, 1392, 53-71. doi: 10.22098/jhs.2013.2555
Jafarian, Ahamad, Measoomy Nia, Safa. (1392). 'Using feed-back neural network method for solving linear fredholm integral equations of the second kind', سامانه مدیریت نشریات علمی, 2(1), pp. 53-71. doi: 10.22098/jhs.2013.2555
Jafarian, Ahamad, Measoomy Nia, Safa. Using feed-back neural network method for solving linear fredholm integral equations of the second kind. سامانه مدیریت نشریات علمی, 1392; 2(1): 53-71. doi: 10.22098/jhs.2013.2555

Using feed-back neural network method for solving linear fredholm integral equations of the second kind

Journal of Hyperstructures
دوره 2، شماره 1، شهریور 2013، صفحه 53-71    اصل مقاله (505.6 K)
نوع مقاله: Research Paper
شناسه دیجیتال (DOI): 10.22098/jhs.2013.2555
نویسندگان
Ahamad Jafarian* ؛ Safa Measoomy Nia
Department of Mathematics, Urmia Branch, Islamic Azad University, Urmia, Iran
چکیده
In this paper a new method for finding the solution of Fredholm integral equation based on hybrid neural networks have presented. The proposed neural net can get a real input vector and calculates its corresponding output vector. Next a learning algorithm based on the gradient descent method has been defined for adjusting the connection weights. Eventually, we have showed this method in comparison with some numerical methods provides solutions with good generalization and high accuracy. The method is illustrated by several examples with computer simulations.
کلیدواژه‌ها
Fredholm integral equations؛ Hybrid neural nets؛ Feed-back neural networks (FNN)
آمار
تعداد مشاهده مقاله: 40
تعداد دریافت فایل اصل مقاله: 65


سامانه مدیریت نشریات علمی. قدرت گرفته از سیناوب