کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
403908 677367 2015 9 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Jackson-type inequalities for spherical neural networks with doubling weights
ترجمه فارسی عنوان
نابرابری نوع جکسون برای شبکه های عصبی کروی با وزن دو برابر شده است
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر هوش مصنوعی
چکیده انگلیسی

Recently, the spherical data processing has emerged in many applications and attracted a lot of attention. Among all the methods for dealing with the spherical data, the spherical neural networks (SNNs) method has been recognized as a very efficient tool due to SNNs possess both good approximation capability and spacial localization property. For better localized approximant, weighted approximation should be considered since different areas of the sphere may play different roles in the approximation process. In this paper, using the minimal Riesz energy points and the spherical cap average operator, we first construct a class of well-localized SNNs with a bounded sigmoidal activation function, and then study their approximation capabilities. More specifically, we establish a Jackson-type error estimate for the weighted SNNs approximation in the metric of LpLp space for the well developed doubling weights.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Neural Networks - Volume 63, March 2015, Pages 57–65
نویسندگان
, , , ,