Energy Function for the One-Unit Oja Algorithm

Qingfu Zhang; Yiu-Wing Leung

doi:10.1109/72.410377

Energy Function for the One-Unit Oja Algorithm

Qingfu Zhang
, Yiu-Wing Leung

Research output: Journal Publications and Reviews › RGC 22 - Publication in policy or professional journal

14 Citations (Scopus)

Abstract

The one-unit Oja algorithm plays a very important role in the study of principal component analysis neural networks. In this letter, we propose an energy function whose steepest descent direction (i.e., negative gradient direction) is the same as the average evolution direction of the one-unit Oja algorithm, and the energy function has two global minimal points corresponding to the two converged points of the one-unit Oja algorithm and it has no other local minimal points. © 1995 IEEE

Original language	English
Pages (from-to)	1291-1293
Journal	IEEE Transactions on Neural Networks
Volume	6
Issue number	5
DOIs	https://doi.org/10.1109/72.410377
Publication status	Published - Sept 1995
Externally published	Yes

Access Output

10.1109/72.410377

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{07a445035fbe44979cd1ea890a386e72,

title = "Energy Function for the One-Unit Oja Algorithm",

abstract = "The one-unit Oja algorithm plays a very important role in the study of principal component analysis neural networks. In this letter, we propose an energy function whose steepest descent direction (i.e., negative gradient direction) is the same as the average evolution direction of the one-unit Oja algorithm, and the energy function has two global minimal points corresponding to the two converged points of the one-unit Oja algorithm and it has no other local minimal points. {\textcopyright} 1995 IEEE",

author = "Qingfu Zhang and Yiu-Wing Leung",

year = "1995",

month = sep,

doi = "10.1109/72.410377",

language = "English",

volume = "6",

pages = "1291--1293",

journal = "IEEE Transactions on Neural Networks",

issn = "1045-9227",

publisher = "IEEE Computational Intelligence Society",

number = "5",

}

TY - JOUR

T1 - Energy Function for the One-Unit Oja Algorithm

AU - Zhang, Qingfu

AU - Leung, Yiu-Wing

PY - 1995/9

Y1 - 1995/9

N2 - The one-unit Oja algorithm plays a very important role in the study of principal component analysis neural networks. In this letter, we propose an energy function whose steepest descent direction (i.e., negative gradient direction) is the same as the average evolution direction of the one-unit Oja algorithm, and the energy function has two global minimal points corresponding to the two converged points of the one-unit Oja algorithm and it has no other local minimal points. © 1995 IEEE

AB - The one-unit Oja algorithm plays a very important role in the study of principal component analysis neural networks. In this letter, we propose an energy function whose steepest descent direction (i.e., negative gradient direction) is the same as the average evolution direction of the one-unit Oja algorithm, and the energy function has two global minimal points corresponding to the two converged points of the one-unit Oja algorithm and it has no other local minimal points. © 1995 IEEE

UR - https://www.scopus.com/pages/publications/0029378292

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-0029378292&origin=recordpage

U2 - 10.1109/72.410377

DO - 10.1109/72.410377

M3 - RGC 22 - Publication in policy or professional journal

SN - 1045-9227

VL - 6

SP - 1291

EP - 1293

JO - IEEE Transactions on Neural Networks

JF - IEEE Transactions on Neural Networks

IS - 5

ER -

Energy Function for the One-Unit Oja Algorithm

Abstract

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this