首页 | 本学科首页   官方微博 | 高级检索  
     


Degree of approximation by superpositions of a sigmoidal function
Authors:Chen Debao
Affiliation:(1) Department of Mathematics, University of Texas at Austin, 78712 Austin, TX, U.S.A.
Abstract:In this paper we study the degree of approximation by superpositions of a sigmoidal function. We mainly consider the univariate case. If f is a continuous function, we prove that for any bounded sigmoidal function σ, 
$$sigma ,d_{n,sigma } (f) leqslant ||sigma ||omega (f,frac{1}{{n + 1}})$$
. For the Heaviside function H(x), we prove that 
$$d_{n,H} (f) leqslant omega (f,frac{1}{{2(n + 1)}})$$
. If f is a continuous function of bounded variation, we prove that 
$$d_{n,sigma } (f) leqslant frac{{||sigma ||}}{{(n + 1)}})V(f)$$
and 
$$d_{n,H}  leqslant (f,frac{1}{{2(n + 1)}})V(f)$$
. For he Heaviside function, the coefficient 1 and the approximation orders are the best possible. We compare these results with the classical Jackson and Bernstein theorems, and make some conjectures for further study.
Keywords:
本文献已被 SpringerLink 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号