Error Estimate for Spherical Neural Networks Interpolation

Shaobo Lin; Jinshan Zeng; Zongben Xu

doi:10.1007/s11063-014-9361-x

Error Estimate for Spherical Neural Networks Interpolation

Shaobo Lin
, Jinshan Zeng
, Zongben Xu

Wenzhou University
Xi'an Jiaotong University

Research output: Contribution to journal › Article › peer-review

7 Scopus citations

Abstract

We present a type of spherical neural network (SNN) with bounded sigmoidal activation function and study its interpolation capability. We find that the provided SNN can exactly interpolate the training samples. Furthermore, based on the special structure of the presented SNN, we can bound the interpolation error by the modulus of smoothness of the target function, which is different from the previous results on the spherical scattered data interpolation problem.

Original language	English
Pages (from-to)	369-379
Number of pages	11
Journal	Neural Processing Letters
Volume	42
Issue number	2
DOIs	https://doi.org/10.1007/s11063-014-9361-x
State	Published - 31 Oct 2015

Keywords

Error estimate
Exact interpolation
Sphere
Spherical neural network

Access to Document

10.1007/s11063-014-9361-x

Cite this

@article{ad015c49bc5a4651b6b5eb265e519d8a,

title = "Error Estimate for Spherical Neural Networks Interpolation",

abstract = "We present a type of spherical neural network (SNN) with bounded sigmoidal activation function and study its interpolation capability. We find that the provided SNN can exactly interpolate the training samples. Furthermore, based on the special structure of the presented SNN, we can bound the interpolation error by the modulus of smoothness of the target function, which is different from the previous results on the spherical scattered data interpolation problem.",

keywords = "Error estimate, Exact interpolation, Sphere, Spherical neural network",

author = "Shaobo Lin and Jinshan Zeng and Zongben Xu",

note = "Publisher Copyright: {\textcopyright} 2014, Springer Science+Business Media New York.",

year = "2015",

month = oct,

day = "31",

doi = "10.1007/s11063-014-9361-x",

language = "英语",

volume = "42",

pages = "369--379",

journal = "Neural Processing Letters",

issn = "1370-4621",

publisher = "Springer Netherlands",

number = "2",

}

TY - JOUR

T1 - Error Estimate for Spherical Neural Networks Interpolation

AU - Lin, Shaobo

AU - Zeng, Jinshan

AU - Xu, Zongben

PY - 2015/10/31

Y1 - 2015/10/31

N2 - We present a type of spherical neural network (SNN) with bounded sigmoidal activation function and study its interpolation capability. We find that the provided SNN can exactly interpolate the training samples. Furthermore, based on the special structure of the presented SNN, we can bound the interpolation error by the modulus of smoothness of the target function, which is different from the previous results on the spherical scattered data interpolation problem.

AB - We present a type of spherical neural network (SNN) with bounded sigmoidal activation function and study its interpolation capability. We find that the provided SNN can exactly interpolate the training samples. Furthermore, based on the special structure of the presented SNN, we can bound the interpolation error by the modulus of smoothness of the target function, which is different from the previous results on the spherical scattered data interpolation problem.

KW - Error estimate

KW - Exact interpolation

KW - Sphere

KW - Spherical neural network

UR - https://www.scopus.com/pages/publications/84940596713

U2 - 10.1007/s11063-014-9361-x

DO - 10.1007/s11063-014-9361-x

M3 - 文章

AN - SCOPUS:84940596713

SN - 1370-4621

VL - 42

SP - 369

EP - 379

JO - Neural Processing Letters

JF - Neural Processing Letters

IS - 2

ER -

Error Estimate for Spherical Neural Networks Interpolation

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this