A Preselection-Based Fast Support Vector Machine Learning for Large-Scale Pattern Sets using Compressed Relative Neighborhood Graph

Masanori Goto, Ryosuke Ishida, Seiichi Uchida

Research output: Contribution to journalArticle

Abstract

We propose a pre-selection method for training support vector machines (SVM) with a largescale dataset. Specifically, the proposed method selects patterns around the class boundary and the selected data is fed to train an SVM. For the selection, that is, searching for boundary patterns, we utilize a compressed representation of relative neighborhood graph (Clustered-RNG). A Clustered-RNG is a network of neighboring patterns which have a different class label and thus, we can find boundary patterns between different classes. Through large-scale handwritten digit pattern recognition experiments, we show that the proposed pre-selection method accelerates SVM training process 10 times faster without degrading recognition accuracy.

Original languageEnglish
Pages (from-to)1-7
Number of pages7
JournalResearch Reports on Information Science and Electrical Engineering of Kyushu University
Volume22
Issue number1
Publication statusPublished - Jan 1 2017

Fingerprint

Support vector machines
Learning systems
Pattern recognition
Labels
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Electrical and Electronic Engineering

Cite this

@article{d8dd69edbcc14affbf825cc3ef000a27,
title = "A Preselection-Based Fast Support Vector Machine Learning for Large-Scale Pattern Sets using Compressed Relative Neighborhood Graph",
abstract = "We propose a pre-selection method for training support vector machines (SVM) with a largescale dataset. Specifically, the proposed method selects patterns around the class boundary and the selected data is fed to train an SVM. For the selection, that is, searching for boundary patterns, we utilize a compressed representation of relative neighborhood graph (Clustered-RNG). A Clustered-RNG is a network of neighboring patterns which have a different class label and thus, we can find boundary patterns between different classes. Through large-scale handwritten digit pattern recognition experiments, we show that the proposed pre-selection method accelerates SVM training process 10 times faster without degrading recognition accuracy.",
author = "Masanori Goto and Ryosuke Ishida and Seiichi Uchida",
year = "2017",
month = "1",
day = "1",
language = "English",
volume = "22",
pages = "1--7",
journal = "Research Reports on Information Science and Electrical Engineering of Kyushu University",
issn = "1342-3819",
publisher = "Kyushu University, Faculty of Science",
number = "1",

}

TY - JOUR

T1 - A Preselection-Based Fast Support Vector Machine Learning for Large-Scale Pattern Sets using Compressed Relative Neighborhood Graph

AU - Goto, Masanori

AU - Ishida, Ryosuke

AU - Uchida, Seiichi

PY - 2017/1/1

Y1 - 2017/1/1

N2 - We propose a pre-selection method for training support vector machines (SVM) with a largescale dataset. Specifically, the proposed method selects patterns around the class boundary and the selected data is fed to train an SVM. For the selection, that is, searching for boundary patterns, we utilize a compressed representation of relative neighborhood graph (Clustered-RNG). A Clustered-RNG is a network of neighboring patterns which have a different class label and thus, we can find boundary patterns between different classes. Through large-scale handwritten digit pattern recognition experiments, we show that the proposed pre-selection method accelerates SVM training process 10 times faster without degrading recognition accuracy.

AB - We propose a pre-selection method for training support vector machines (SVM) with a largescale dataset. Specifically, the proposed method selects patterns around the class boundary and the selected data is fed to train an SVM. For the selection, that is, searching for boundary patterns, we utilize a compressed representation of relative neighborhood graph (Clustered-RNG). A Clustered-RNG is a network of neighboring patterns which have a different class label and thus, we can find boundary patterns between different classes. Through large-scale handwritten digit pattern recognition experiments, we show that the proposed pre-selection method accelerates SVM training process 10 times faster without degrading recognition accuracy.

UR - http://www.scopus.com/inward/record.url?scp=85016987386&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016987386&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85016987386

VL - 22

SP - 1

EP - 7

JO - Research Reports on Information Science and Electrical Engineering of Kyushu University

JF - Research Reports on Information Science and Electrical Engineering of Kyushu University

SN - 1342-3819

IS - 1

ER -