Identifying surfaces of low dimensions in high dimensional data

Agnar Høskuldsson

Identifying surfaces of low dimensions in high dimensional data

Agnar Høskuldsson

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

Methods are presented that find a nonlinear subspace in low dimensions that describe data given by many variables. The methods include nonlinear extensions of Principal Component Analysis and extensions of linear regression analysis. It is shown by examples that these methods give more reliable results than similar techniques, where variables are selected and polynomials in those used.

Original language	English
Title of host publication	The Expansion Method Symposium
Place of Publication	Odense
Publisher	Odense University
Publication date	1996
Publication status	Published - 1996

OpenUrl availability

Full text

Cite this

@inproceedings{6b7b0f680eda4809bf6e4b1bec8a012d,

title = "Identifying surfaces of low dimensions in high dimensional data",

abstract = "Methods are presented that find a nonlinear subspace in low dimensions that describe data given by many variables. The methods include nonlinear extensions of Principal Component Analysis and extensions of linear regression analysis. It is shown by examples that these methods give more reliable results than similar techniques, where variables are selected and polynomials in those used.",

author = "Agnar H{\o}skuldsson",

year = "1996",

language = "English",

booktitle = "The Expansion Method Symposium",

publisher = "Odense University",

}

TY - GEN

T1 - Identifying surfaces of low dimensions in high dimensional data

AU - Høskuldsson, Agnar

PY - 1996

Y1 - 1996

N2 - Methods are presented that find a nonlinear subspace in low dimensions that describe data given by many variables. The methods include nonlinear extensions of Principal Component Analysis and extensions of linear regression analysis. It is shown by examples that these methods give more reliable results than similar techniques, where variables are selected and polynomials in those used.

AB - Methods are presented that find a nonlinear subspace in low dimensions that describe data given by many variables. The methods include nonlinear extensions of Principal Component Analysis and extensions of linear regression analysis. It is shown by examples that these methods give more reliable results than similar techniques, where variables are selected and polynomials in those used.

M3 - Article in proceedings

BT - The Expansion Method Symposium

PB - Odense University

CY - Odense

ER -