Growing RBF structures using self-organizing maps

Qingyu Xiong, Kotaro Hirasawa, Takayuki Furuzuki, Junichi Murata

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

1 Citation (Scopus)

Abstract

We present a novel growing RBF network structure using SOM in this paper. It consists of SOM and RBF networks respectively. The SOM performs unsupervised learning and also the weight vectors belonging to its output nodes are transmitted to the hidden nodes in the RBF networks as the centers of RBF activation functions. as a result one to one correspondence relationship is realized between the output nodes in SOM and the hidden nodes in RBF networks. The RBF networks perform supervised training using delta rule. Therefore, the current output errors in the RBF networks can be used to determine where to insert a new SOM unit according to the rule. This also makes it possible to make the RBF networks grow until a performance criterion is fulfilled or until a desired network size is obtained. The simulations on the two-spirals benchmark are shown to prove the proposed networks have good performance.

Original languageEnglish
Title of host publicationProceedings - IEEE International Workshop on Robot and Human Interactive Communication
Pages107-109
Number of pages3
DOIs
Publication statusPublished - 2000
Externally publishedYes
Event9th IEEE International Workshop on Robot and Human Interactive Communication, IEEE RO-MAN 2000 - Osaka
Duration: 2000 Sep 272000 Sep 29

Other

Other9th IEEE International Workshop on Robot and Human Interactive Communication, IEEE RO-MAN 2000
CityOsaka
Period00/9/2700/9/29

Fingerprint

Radial basis function networks
Self organizing maps
Unsupervised learning
Chemical activation

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Human-Computer Interaction

Cite this

Xiong, Q., Hirasawa, K., Furuzuki, T., & Murata, J. (2000). Growing RBF structures using self-organizing maps. In Proceedings - IEEE International Workshop on Robot and Human Interactive Communication (pp. 107-109). [892479] https://doi.org/10.1109/ROMAN.2000.892479

Growing RBF structures using self-organizing maps. / Xiong, Qingyu; Hirasawa, Kotaro; Furuzuki, Takayuki; Murata, Junichi.

Proceedings - IEEE International Workshop on Robot and Human Interactive Communication. 2000. p. 107-109 892479.

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

Xiong, Q, Hirasawa, K, Furuzuki, T & Murata, J 2000, Growing RBF structures using self-organizing maps. in Proceedings - IEEE International Workshop on Robot and Human Interactive Communication., 892479, pp. 107-109, 9th IEEE International Workshop on Robot and Human Interactive Communication, IEEE RO-MAN 2000, Osaka, 00/9/27. https://doi.org/10.1109/ROMAN.2000.892479
Xiong Q, Hirasawa K, Furuzuki T, Murata J. Growing RBF structures using self-organizing maps. In Proceedings - IEEE International Workshop on Robot and Human Interactive Communication. 2000. p. 107-109. 892479 https://doi.org/10.1109/ROMAN.2000.892479
Xiong, Qingyu ; Hirasawa, Kotaro ; Furuzuki, Takayuki ; Murata, Junichi. / Growing RBF structures using self-organizing maps. Proceedings - IEEE International Workshop on Robot and Human Interactive Communication. 2000. pp. 107-109
@inproceedings{e3359334b56244bb9e393ae8ebd922f8,
title = "Growing RBF structures using self-organizing maps",
abstract = "We present a novel growing RBF network structure using SOM in this paper. It consists of SOM and RBF networks respectively. The SOM performs unsupervised learning and also the weight vectors belonging to its output nodes are transmitted to the hidden nodes in the RBF networks as the centers of RBF activation functions. as a result one to one correspondence relationship is realized between the output nodes in SOM and the hidden nodes in RBF networks. The RBF networks perform supervised training using delta rule. Therefore, the current output errors in the RBF networks can be used to determine where to insert a new SOM unit according to the rule. This also makes it possible to make the RBF networks grow until a performance criterion is fulfilled or until a desired network size is obtained. The simulations on the two-spirals benchmark are shown to prove the proposed networks have good performance.",
author = "Qingyu Xiong and Kotaro Hirasawa and Takayuki Furuzuki and Junichi Murata",
year = "2000",
doi = "10.1109/ROMAN.2000.892479",
language = "English",
isbn = "078036273X",
pages = "107--109",
booktitle = "Proceedings - IEEE International Workshop on Robot and Human Interactive Communication",

}

TY - GEN

T1 - Growing RBF structures using self-organizing maps

AU - Xiong, Qingyu

AU - Hirasawa, Kotaro

AU - Furuzuki, Takayuki

AU - Murata, Junichi

PY - 2000

Y1 - 2000

N2 - We present a novel growing RBF network structure using SOM in this paper. It consists of SOM and RBF networks respectively. The SOM performs unsupervised learning and also the weight vectors belonging to its output nodes are transmitted to the hidden nodes in the RBF networks as the centers of RBF activation functions. as a result one to one correspondence relationship is realized between the output nodes in SOM and the hidden nodes in RBF networks. The RBF networks perform supervised training using delta rule. Therefore, the current output errors in the RBF networks can be used to determine where to insert a new SOM unit according to the rule. This also makes it possible to make the RBF networks grow until a performance criterion is fulfilled or until a desired network size is obtained. The simulations on the two-spirals benchmark are shown to prove the proposed networks have good performance.

AB - We present a novel growing RBF network structure using SOM in this paper. It consists of SOM and RBF networks respectively. The SOM performs unsupervised learning and also the weight vectors belonging to its output nodes are transmitted to the hidden nodes in the RBF networks as the centers of RBF activation functions. as a result one to one correspondence relationship is realized between the output nodes in SOM and the hidden nodes in RBF networks. The RBF networks perform supervised training using delta rule. Therefore, the current output errors in the RBF networks can be used to determine where to insert a new SOM unit according to the rule. This also makes it possible to make the RBF networks grow until a performance criterion is fulfilled or until a desired network size is obtained. The simulations on the two-spirals benchmark are shown to prove the proposed networks have good performance.

UR - http://www.scopus.com/inward/record.url?scp=33646675164&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33646675164&partnerID=8YFLogxK

U2 - 10.1109/ROMAN.2000.892479

DO - 10.1109/ROMAN.2000.892479

M3 - Conference contribution

AN - SCOPUS:33646675164

SN - 078036273X

SN - 9780780362734

SP - 107

EP - 109

BT - Proceedings - IEEE International Workshop on Robot and Human Interactive Communication

ER -