کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
4643259 | 1341374 | 2006 | 13 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
Improved sign-based learning algorithm derived by the composite nonlinear Jacobi process
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
کلمات کلیدی
موضوعات مرتبط
مهندسی و علوم پایه
ریاضیات
ریاضیات کاربردی
پیش نمایش صفحه اول مقاله
![عکس صفحه اول مقاله: Improved sign-based learning algorithm derived by the composite nonlinear Jacobi process Improved sign-based learning algorithm derived by the composite nonlinear Jacobi process](/preview/png/4643259.png)
چکیده انگلیسی
In this paper a globally convergent first-order training algorithm is proposed that uses sign-based information of the batch error measure in the framework of the nonlinear Jacobi process. This approach allows us to equip the recently proposed Jacobi–Rprop method with the global convergence property, i.e. convergence to a local minimizer from any initial starting point. We also propose a strategy that ensures the search direction of the globally convergent Jacobi–Rprop is a descent one. The behaviour of the algorithm is empirically investigated in eight benchmark problems. Simulation results verify that there are indeed improvements on the convergence success of the algorithm.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Journal of Computational and Applied Mathematics - Volume 191, Issue 2, 1 July 2006, Pages 166–178
Journal: Journal of Computational and Applied Mathematics - Volume 191, Issue 2, 1 July 2006, Pages 166–178
نویسندگان
Aristoklis D. Anastasiadis, George D. Magoulas, Michael N. Vrahatis,