Unified stabilization approach to principal and minor components extraction algorithms

Tianping Chen; Shun Ichi Amari

doi:10.1016/S0893-6080(01)00116-2

Unified stabilization approach to principal and minor components extraction algorithms

Tianping Chen
, Shun Ichi Amari

Fudan University
RIKEN

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

75 Scopus citations

Abstract

Principal component and minor component extractions provide powerful techniques in many information processing fields. There have been proposed a number of algorithms for principal and minor component (or subspace) extraction, which have different dynamical behaviors. In this paper, we give rigorous stability analysis of these algorithms, obtaining a unified insight view on the dynamical behaviors of various algorithms.

Original language	English
Pages (from-to)	1377-1387
Number of pages	11
Journal	Neural Networks
Volume	14
Issue number	10
DOIs	https://doi.org/10.1016/S0893-6080(01)00116-2
State	Published - 2001
Externally published	Yes

Keywords

Minor component extraction
Natural gradient
Principal component extraction
Singular value decomposition
Stability of dynamical system

Access to Document

10.1016/S0893-6080(01)00116-2

Cite this

@article{6c8255ed8a5b44c1865849dd708859cb,

title = "Unified stabilization approach to principal and minor components extraction algorithms",

abstract = "Principal component and minor component extractions provide powerful techniques in many information processing fields. There have been proposed a number of algorithms for principal and minor component (or subspace) extraction, which have different dynamical behaviors. In this paper, we give rigorous stability analysis of these algorithms, obtaining a unified insight view on the dynamical behaviors of various algorithms.",

keywords = "Minor component extraction, Natural gradient, Principal component extraction, Singular value decomposition, Stability of dynamical system",

author = "Tianping Chen and Amari, \{Shun Ichi\}",

year = "2001",

doi = "10.1016/S0893-6080(01)00116-2",

language = "英語",

volume = "14",

pages = "1377--1387",

journal = "Neural Networks",

issn = "0893-6080",

publisher = "Elsevier Ltd",

number = "10",

}

TY - JOUR

T1 - Unified stabilization approach to principal and minor components extraction algorithms

AU - Chen, Tianping

AU - Amari, Shun Ichi

PY - 2001

Y1 - 2001

N2 - Principal component and minor component extractions provide powerful techniques in many information processing fields. There have been proposed a number of algorithms for principal and minor component (or subspace) extraction, which have different dynamical behaviors. In this paper, we give rigorous stability analysis of these algorithms, obtaining a unified insight view on the dynamical behaviors of various algorithms.

AB - Principal component and minor component extractions provide powerful techniques in many information processing fields. There have been proposed a number of algorithms for principal and minor component (or subspace) extraction, which have different dynamical behaviors. In this paper, we give rigorous stability analysis of these algorithms, obtaining a unified insight view on the dynamical behaviors of various algorithms.

KW - Minor component extraction

KW - Natural gradient

KW - Principal component extraction

KW - Singular value decomposition

KW - Stability of dynamical system

UR - https://www.scopus.com/pages/publications/0035187852

U2 - 10.1016/S0893-6080(01)00116-2

DO - 10.1016/S0893-6080(01)00116-2

M3 - 記事

C2 - 11771718

AN - SCOPUS:0035187852

SN - 0893-6080

VL - 14

SP - 1377

EP - 1387

JO - Neural Networks

JF - Neural Networks

IS - 10

ER -

Unified stabilization approach to principal and minor components extraction algorithms

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this