2011
DOI: 10.1007/s11425-011-4262-1
|View full text |Cite
|
Sign up to set email alerts
|

The essential rate of approximation for radial function manifold

Abstract: In this paper, we investigate the radial function manifolds generated by a linear combination of radial functions. Let W r p (B d ) be the usual Sobolev class of functions on the unit ball B d . We study the deviation from the radial function manifolds to W r p (B d ). Our results show that the upper and lower bounds of approximation by a linear combination of radial functions are asymptotically identical. We also find that the radial function manifolds and ridge function manifolds generated by a linear combin… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
4
0

Year Published

2013
2013
2015
2015

Publication Types

Select...
2

Relationship

2
0

Authors

Journals

citations
Cited by 2 publications
(4 citation statements)
references
References 17 publications
0
4
0
Order By: Relevance
“…The relationship between RBFN and polynomial approximation has already studied in Maiorov (2003) and Lin et al (2011a). In Maiorov (2003), Maiorov studied the approximation properties of the radial function manifold G N whose elements take the form as…”
Section: Theorem 1 Let N and N Be Any Natural Numbers Satisfyingmentioning
confidence: 99%
See 2 more Smart Citations
“…The relationship between RBFN and polynomial approximation has already studied in Maiorov (2003) and Lin et al (2011a). In Maiorov (2003), Maiorov studied the approximation properties of the radial function manifold G N whose elements take the form as…”
Section: Theorem 1 Let N and N Be Any Natural Numbers Satisfyingmentioning
confidence: 99%
“…They proved that the approximation capability of G N is not worse than that of polynomials of degrees at most n provided N ≥ (2d Lin et al (2011a) deduced that if the target function is radial and N ∼ n d−1 , then the approximation rate of polynomials is also not slower than that of G N . Noting that the utilized approximants in (6) are linear combinations of different univariate functions, it is difficult to determine the capacity of G N .…”
Section: Theorem 1 Let N and N Be Any Natural Numbers Satisfyingmentioning
confidence: 99%
See 1 more Smart Citation
“…In [12] [13] [14] [15], the following feed-forward networks defined on the unit sphere were considered and some approximation properties were studied:…”
Section: Introductionmentioning
confidence: 99%