Fast design algorithm for competitive learning

Wen Jyi Hwang; Faa Jeng Lin; Yi Chong Zeng

doi:10.1049/el:19971010

Fast design algorithm for competitive learning

Wen Jyi Hwang, Faa Jeng Lin, Yi Chong Zeng

Department of Electrical Engineering

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

8 Scopus citations

Abstract

The authors present a new, fast computation algorithm which significantly reduces the training time of the competitive learning (CL) algorithm without sacrificing its performance. The training process is performed in the wavelet domain to identify the winning neural units with a small number of multiplications. Simulation results show that in many cases the algorithm requires < 10% of the computational time required by traditional CL algorithms.

Original language	English
Pages (from-to)	1469-1471
Number of pages	3
Journal	Electronics Letters
Volume	33
Issue number	17
DOIs	https://doi.org/10.1049/el:19971010
State	Published - 14 Aug 1997

Keywords

Learning systems
Neural networks
Wavelet transforms

Access to Document

10.1049/el:19971010

Cite this

@article{41292dce3da845d988a3f01fb8c6ada8,

title = "Fast design algorithm for competitive learning",

abstract = "The authors present a new, fast computation algorithm which significantly reduces the training time of the competitive learning (CL) algorithm without sacrificing its performance. The training process is performed in the wavelet domain to identify the winning neural units with a small number of multiplications. Simulation results show that in many cases the algorithm requires < 10% of the computational time required by traditional CL algorithms.",

keywords = "Learning systems, Neural networks, Wavelet transforms",

author = "Hwang, {Wen Jyi} and Lin, {Faa Jeng} and Zeng, {Yi Chong}",

year = "1997",

month = aug,

day = "14",

doi = "10.1049/el:19971010",

language = "???core.languages.en_GB???",

volume = "33",

pages = "1469--1471",

journal = "Electronics Letters",

issn = "0013-5194",

number = "17",

}

TY - JOUR

T1 - Fast design algorithm for competitive learning

AU - Hwang, Wen Jyi

AU - Lin, Faa Jeng

AU - Zeng, Yi Chong

PY - 1997/8/14

Y1 - 1997/8/14

N2 - The authors present a new, fast computation algorithm which significantly reduces the training time of the competitive learning (CL) algorithm without sacrificing its performance. The training process is performed in the wavelet domain to identify the winning neural units with a small number of multiplications. Simulation results show that in many cases the algorithm requires < 10% of the computational time required by traditional CL algorithms.

AB - The authors present a new, fast computation algorithm which significantly reduces the training time of the competitive learning (CL) algorithm without sacrificing its performance. The training process is performed in the wavelet domain to identify the winning neural units with a small number of multiplications. Simulation results show that in many cases the algorithm requires < 10% of the computational time required by traditional CL algorithms.

KW - Learning systems

KW - Neural networks

KW - Wavelet transforms

UR - http://www.scopus.com/inward/record.url?scp=0031199294&partnerID=8YFLogxK

U2 - 10.1049/el:19971010

DO - 10.1049/el:19971010

M3 - 期刊論文

AN - SCOPUS:0031199294

SN - 0013-5194

VL - 33

SP - 1469

EP - 1471

JO - Electronics Letters

JF - Electronics Letters

IS - 17

ER -

Fast design algorithm for competitive learning

Abstract

Keywords

Access to Document

Fingerprint

Cite this