...
首页> 外文期刊>Journal of complexity >Weighted quadrature formulas and approximation by zonal function networks on the sphere
【24h】

Weighted quadrature formulas and approximation by zonal function networks on the sphere

机译:球面上的加权正交公式和区域函数网络的逼近

获取原文
获取原文并翻译 | 示例
           

摘要

Let q ≥ 1 be an integer, S~q be the unit sphere embedded in the Euclidean space R~(q+1). A zonal function (ZF) network with an activation function φ : [-1,1] → R and n neurons is a function on S~q of the form x |→ ∑_(k=1)~n a_k φ(x · ξ_k), where a_k's are real numbers, ξ_k are points on S~q. We consider the activation functions φ for which the coefficients {φ(l)} in the appropriate ultraspherical polynomial expansion decay as a power of (l +1)~(-1). We construct ZF networks to approximate functions in the Sobolev classes on the unit sphere embedded in a Euclidean space, yielding an optimal order of decay for the degree of approximation in terms of n, compared with the nonlinear re-widths of these classes. Our networks do not require training in the traditional sense. Instead, the network approximating a function is given explicitly as the value of a linear operator at that function. In the case of uniform approximation, our construction utilizes values of the target function at scattered sites. The approximation bounds are used to obtain error bounds on a very general class of quadrature formulas that are exact for the integration of high degree polynomials with respect to a weighted integral. The bounds are better than those expected from a straightforward application of the Sobolev embeddings.
机译:令q≥1为整数,S〜q为嵌入欧氏空间R〜(q + 1)的单位球。具有激活函数φ的区域功能(ZF)网络:[-1,1]→R和n个神经元是S〜q上具有x |→∑_(k = 1)〜n a_kφ(x ·ξ_k),其中a_k是实数,ξ_k是S〜q上的点。我们考虑激活函数φ,在该函数中,适当的超球形多项式展开式中的系数{φ(l)}的幂为(l +1)〜(-1)。我们构造ZF网络以近似嵌入在欧几里德空间中的单位球面上Sobolev类中的函数,与这些类的非线性重宽度相比,对于n的近似程度,它产生了最佳的衰减阶数。我们的网络不需要传统意义上的培训。取而代之的是,将近似逼近函数的网络明确地指定为该函数处线性算子的值。在均匀近似的情况下,我们的构造利用分散位置上目标函数的值。近似界限用于获得非常通用的一类正交公式的误差界限,这些积分对于相对于加权积分的高阶多项式积分准确无误。边界比直接应用Sobolev嵌入所期望的边界要好。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号