کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
405493 | 677651 | 2012 | 8 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
Learning in fully recurrent neural networks by approaching tangent planes to constraint surfaces
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
کلمات کلیدی
موضوعات مرتبط
مهندسی و علوم پایه
مهندسی کامپیوتر
هوش مصنوعی
پیش نمایش صفحه اول مقاله

چکیده انگلیسی
In this paper we present a new variant of the online real time recurrent learning algorithm proposed by Williams and Zipser (1989). Whilst the original algorithm utilises gradient information to guide the search towards the minimum training error, it is very slow in most applications and often gets stuck in local minima of the search space. It is also sensitive to the choice of learning rate and requires careful tuning. The new variant adjusts weights by moving to the tangent planes to constraint surfaces. It is simple to implement and requires no parameters to be set manually. Experimental results show that this new algorithm gives significantly faster convergence whilst avoiding problems like local minima.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Neural Networks - Volume 34, October 2012, Pages 72–79
Journal: Neural Networks - Volume 34, October 2012, Pages 72–79
نویسندگان
P. May, E. Zhou, C.W. Lee,