Variable-density Self-Organizing Map for incremental learning

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

We propose a new incremental learning method of Self-Organizing Map. Basically, there are three problems in the incremental learning of Self-Organizing Map: 1. depletion of neurons, 2. oblivion of training data previously given, 3. destruction of topological relationship among training samples. Weight-fixed neurons and weight-quasi-fixed neurons are very effective for the second problem. However the other problems still remain. Therefore, we improve the incremental learning method with weight-fixed neurons and weight-quasi-fixed neurons. We solve the problems by introducing a mechanism to increase the number of neurons effectively in the incremental learning process.

Original languageEnglish
Title of host publicationWSOM 2007 - 6th Int. Workshop on Self-Organizing Maps
Publication statusPublished - 2007
Event6th Int. Workshop on Self-Organizing Maps, WSOM 2007 - Bielefeld, Germany
Duration: Sep 3 2007Sep 6 2007

Other

Other6th Int. Workshop on Self-Organizing Maps, WSOM 2007
CountryGermany
CityBielefeld
Period9/3/079/6/07

Fingerprint

Self organizing maps
Neurons

All Science Journal Classification (ASJC) codes

  • Software

Cite this

Shimada, A., & Taniguchi, R-I. (2007). Variable-density Self-Organizing Map for incremental learning. In WSOM 2007 - 6th Int. Workshop on Self-Organizing Maps

Variable-density Self-Organizing Map for incremental learning. / Shimada, Atsushi; Taniguchi, Rin-Ichiro.

WSOM 2007 - 6th Int. Workshop on Self-Organizing Maps. 2007.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Shimada, A & Taniguchi, R-I 2007, Variable-density Self-Organizing Map for incremental learning. in WSOM 2007 - 6th Int. Workshop on Self-Organizing Maps. 6th Int. Workshop on Self-Organizing Maps, WSOM 2007, Bielefeld, Germany, 9/3/07.
Shimada A, Taniguchi R-I. Variable-density Self-Organizing Map for incremental learning. In WSOM 2007 - 6th Int. Workshop on Self-Organizing Maps. 2007
@inproceedings{b2d031d2df774b3fb11f9e43a731a28b,
title = "Variable-density Self-Organizing Map for incremental learning",
abstract = "We propose a new incremental learning method of Self-Organizing Map. Basically, there are three problems in the incremental learning of Self-Organizing Map: 1. depletion of neurons, 2. oblivion of training data previously given, 3. destruction of topological relationship among training samples. Weight-fixed neurons and weight-quasi-fixed neurons are very effective for the second problem. However the other problems still remain. Therefore, we improve the incremental learning method with weight-fixed neurons and weight-quasi-fixed neurons. We solve the problems by introducing a mechanism to increase the number of neurons effectively in the incremental learning process.",
author = "Atsushi Shimada and Rin-Ichiro Taniguchi",
year = "2007",
language = "English",
booktitle = "WSOM 2007 - 6th Int. Workshop on Self-Organizing Maps",

}

TY - GEN

T1 - Variable-density Self-Organizing Map for incremental learning

AU - Shimada, Atsushi

AU - Taniguchi, Rin-Ichiro

PY - 2007

Y1 - 2007

N2 - We propose a new incremental learning method of Self-Organizing Map. Basically, there are three problems in the incremental learning of Self-Organizing Map: 1. depletion of neurons, 2. oblivion of training data previously given, 3. destruction of topological relationship among training samples. Weight-fixed neurons and weight-quasi-fixed neurons are very effective for the second problem. However the other problems still remain. Therefore, we improve the incremental learning method with weight-fixed neurons and weight-quasi-fixed neurons. We solve the problems by introducing a mechanism to increase the number of neurons effectively in the incremental learning process.

AB - We propose a new incremental learning method of Self-Organizing Map. Basically, there are three problems in the incremental learning of Self-Organizing Map: 1. depletion of neurons, 2. oblivion of training data previously given, 3. destruction of topological relationship among training samples. Weight-fixed neurons and weight-quasi-fixed neurons are very effective for the second problem. However the other problems still remain. Therefore, we improve the incremental learning method with weight-fixed neurons and weight-quasi-fixed neurons. We solve the problems by introducing a mechanism to increase the number of neurons effectively in the incremental learning process.

UR - http://www.scopus.com/inward/record.url?scp=84893495503&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893495503&partnerID=8YFLogxK

M3 - Conference contribution

BT - WSOM 2007 - 6th Int. Workshop on Self-Organizing Maps

ER -