کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
6422161 | 1340618 | 2011 | 21 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
Nonmonotone BFGS-trained recurrent neural networks for temporal sequence processing
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: Nonmonotone BFGS-trained recurrent neural networks for temporal sequence processing Nonmonotone BFGS-trained recurrent neural networks for temporal sequence processing](/preview/png/6422161.png)
چکیده انگلیسی
In this paper we propose a nonmonotone approach to recurrent neural networks training for temporal sequence processing applications. This approach allows learning performance to deteriorate in some iterations, nevertheless the network's performance is improved over time. A self-scaling BFGS is equipped with an adaptive nonmonotone technique that employs approximations of the Lipschitz constant and is tested on a set of sequence processing problems. Simulation results show that the proposed algorithm outperforms the BFGS as well as other methods previously applied to these sequences, providing an effective modification that is capable of training recurrent networks of various architectures.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Applied Mathematics and Computation - Volume 217, Issue 12, 15 February 2011, Pages 5421-5441
Journal: Applied Mathematics and Computation - Volume 217, Issue 12, 15 February 2011, Pages 5421-5441
نویسندگان
Chun-Cheng Peng, George D. Magoulas,