Incremental learning in self-organizing map

Research output: Contribution to journalArticle

Abstract

We propose a new incremental learning method of Self-Organizing Map. There are three problems in the incremental learning of Self-Organizing Map; 1. neuron depletion, 2. forgetting previous training data, 3. keeping topology. Weights fixed neurons and weights semi-fixed neurons are very effective for the second problem. However the other problems remain. Therefore, we improve the incremental learning method with weights fixed neurons and weights semi-fixed neurons. Our approach can increment neurons effectively in the incremental learning process.

Original languageEnglish
Pages (from-to)49-54
Number of pages6
JournalResearch Reports on Information Science and Electrical Engineering of Kyushu University
Volume12
Issue number1
Publication statusPublished - Mar 1 2007

Fingerprint

Self organizing maps
Neurons
Topology

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Electrical and Electronic Engineering

Cite this

@article{c120a0351ace4670bb6589c59032cc97,
title = "Incremental learning in self-organizing map",
abstract = "We propose a new incremental learning method of Self-Organizing Map. There are three problems in the incremental learning of Self-Organizing Map; 1. neuron depletion, 2. forgetting previous training data, 3. keeping topology. Weights fixed neurons and weights semi-fixed neurons are very effective for the second problem. However the other problems remain. Therefore, we improve the incremental learning method with weights fixed neurons and weights semi-fixed neurons. Our approach can increment neurons effectively in the incremental learning process.",
author = "Atsushi Shimada and Rin-Ichiro Taniguchi",
year = "2007",
month = "3",
day = "1",
language = "English",
volume = "12",
pages = "49--54",
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 - Incremental learning in self-organizing map

AU - Shimada, Atsushi

AU - Taniguchi, Rin-Ichiro

PY - 2007/3/1

Y1 - 2007/3/1

N2 - We propose a new incremental learning method of Self-Organizing Map. There are three problems in the incremental learning of Self-Organizing Map; 1. neuron depletion, 2. forgetting previous training data, 3. keeping topology. Weights fixed neurons and weights semi-fixed neurons are very effective for the second problem. However the other problems remain. Therefore, we improve the incremental learning method with weights fixed neurons and weights semi-fixed neurons. Our approach can increment neurons effectively in the incremental learning process.

AB - We propose a new incremental learning method of Self-Organizing Map. There are three problems in the incremental learning of Self-Organizing Map; 1. neuron depletion, 2. forgetting previous training data, 3. keeping topology. Weights fixed neurons and weights semi-fixed neurons are very effective for the second problem. However the other problems remain. Therefore, we improve the incremental learning method with weights fixed neurons and weights semi-fixed neurons. Our approach can increment neurons effectively in the incremental learning process.

UR - http://www.scopus.com/inward/record.url?scp=34548043998&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548043998&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:34548043998

VL - 12

SP - 49

EP - 54

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 -