کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
407770 678168 2012 10 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Convergence of an online gradient method with inner-product penalty and adaptive momentum
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر هوش مصنوعی
پیش نمایش صفحه اول مقاله
Convergence of an online gradient method with inner-product penalty and adaptive momentum
چکیده انگلیسی

In this paper, we study the convergence of an online gradient method with inner-product penalty and adaptive momentum for feedforward neural networks, assuming that the training samples are permuted stochastically in each cycle of iteration. Both two-layer and three-layer neural network models are considered, and two convergence theorems are established. Sufficient conditions are proposed to prove weak and strong convergence results. The algorithm is applied to the classical two-spiral problem and identification of Gabor function problem to support these theoretical findings.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Neurocomputing - Volume 77, Issue 1, 1 February 2012, Pages 243–252
نویسندگان
, , , ,