A topology preserving neural network for nonstationary distributions

Taira Nakajima; Hiroyuki Takizawa; Hiroaki Kobayashi; Tadao Nakamura

A topology preserving neural network for nonstationary distributions

Taira Nakajima, Hiroyuki Takizawa, Hiroaki Kobayashi, Tadao Nakamura

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

Abstract

We propose a learning algorithm for selforganizing neural networks to form a topology preserving map from an input manifold whose topology may dynamically change. Experimental results show that the network using the proposed algorithm can rapidly adjust itself to represent the topology of nonstationary input distributions.

Original language	English
Pages (from-to)	1131-1135
Number of pages	5
Journal	IEICE Transactions on Information and Systems
Volume	E82-D
Issue number	7
Publication status	Published - 1999 Jan 1

Keywords

Competitive Hebbian learning rule
Law of the jungle mechanism
Neural networks
Nonstationary probability distribution
Self-organizing map

ASJC Scopus subject areas

Software
Hardware and Architecture
Computer Vision and Pattern Recognition
Electrical and Electronic Engineering
Artificial Intelligence

Access to Document

Fingerprint Dive into the research topics of 'A topology preserving neural network for nonstationary distributions'. Together they form a unique fingerprint.

Cite this

@article{ac7c06303c204bb5b9efb71b1e2b5151,

title = "A topology preserving neural network for nonstationary distributions",

abstract = "We propose a learning algorithm for selforganizing neural networks to form a topology preserving map from an input manifold whose topology may dynamically change. Experimental results show that the network using the proposed algorithm can rapidly adjust itself to represent the topology of nonstationary input distributions.",

keywords = "Competitive Hebbian learning rule, Law of the jungle mechanism, Neural networks, Nonstationary probability distribution, Self-organizing map",

author = "Taira Nakajima and Hiroyuki Takizawa and Hiroaki Kobayashi and Tadao Nakamura",

year = "1999",

month = jan,

day = "1",

language = "English",

volume = "E82-D",

pages = "1131--1135",

journal = "IEICE Transactions on Information and Systems",

issn = "0916-8532",

publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",

number = "7",

}

TY - JOUR

T1 - A topology preserving neural network for nonstationary distributions

AU - Nakajima, Taira

AU - Takizawa, Hiroyuki

AU - Kobayashi, Hiroaki

AU - Nakamura, Tadao

PY - 1999/1/1

Y1 - 1999/1/1

N2 - We propose a learning algorithm for selforganizing neural networks to form a topology preserving map from an input manifold whose topology may dynamically change. Experimental results show that the network using the proposed algorithm can rapidly adjust itself to represent the topology of nonstationary input distributions.

AB - We propose a learning algorithm for selforganizing neural networks to form a topology preserving map from an input manifold whose topology may dynamically change. Experimental results show that the network using the proposed algorithm can rapidly adjust itself to represent the topology of nonstationary input distributions.

KW - Competitive Hebbian learning rule

KW - Law of the jungle mechanism

KW - Neural networks

KW - Nonstationary probability distribution

KW - Self-organizing map

UR - http://www.scopus.com/inward/record.url?scp=0033160074&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033160074&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0033160074

VL - E82-D

SP - 1131

EP - 1135

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 7

ER -