A pruning structure of self-organizing HCMAC neural network classifier

Chih Ming Chen; Chin Ming Hong; Yung Feng Lu

doi:10.1109/IJCNN.2004.1380042

A pruning structure of self-organizing HCMAC neural network classifier

Chih Ming Chen^*, Chin Ming Hong, Yung Feng Lu

^*此作品的通信作者

電機工程學系

研究成果: 書貢獻/報告類型 › 會議論文篇章

2 引文斯高帕斯（Scopus）

摘要

A self-organizing HCMAC neural network was proposed to solve high dimensional pattern classification problems well in our previous work. However, a large amount of redundant GCMAC nodes might be constructed due to the expansion approach of full binary tree topology. Therefore, this study presents a pruning structure of self-organizing HCMAC neural network to solve this problem. Experimental results show the proposed pruning structure not only can largely reduce memory requirement, but also keep fast training speed and has higher pattern classification accuracy rate than the original self-organizing HCMAC neural network does in the most testing benchmark data sets.

原文	英語
主出版物標題	2004 IEEE International Joint Conference on Neural Networks - Proceedings
頁面	861-866
頁數	6
DOIs	https://doi.org/10.1109/IJCNN.2004.1380042
出版狀態	已發佈 - 2004
事件	2004 IEEE International Joint Conference on Neural Networks - Proceedings - Budapest, 匈牙利持續時間: 2004 7月 25 → 2004 7月 29

出版系列

名字	IEEE International Conference on Neural Networks - Conference Proceedings
卷	2
ISSN（列印）	1098-7576

會議

會議	2004 IEEE International Joint Conference on Neural Networks - Proceedings
國家/地區	匈牙利
城市	Budapest
期間	2004/07/25 → 2004/07/29

ASJC Scopus subject areas

軟體

存取文件

10.1109/IJCNN.2004.1380042

其它文件與鏈接

引用此

Chen, CM, Hong, CM & Lu, YF 2004, A pruning structure of self-organizing HCMAC neural network classifier. 於 2004 IEEE International Joint Conference on Neural Networks - Proceedings. IEEE International Conference on Neural Networks - Conference Proceedings, 卷 2, 頁 861-866, 2004 IEEE International Joint Conference on Neural Networks - Proceedings, Budapest, 匈牙利, 2004/07/25. https://doi.org/10.1109/IJCNN.2004.1380042

@inproceedings{5fc5cd8239e949b6a3f3b64b08b17a26,

title = "A pruning structure of self-organizing HCMAC neural network classifier",

abstract = "A self-organizing HCMAC neural network was proposed to solve high dimensional pattern classification problems well in our previous work. However, a large amount of redundant GCMAC nodes might be constructed due to the expansion approach of full binary tree topology. Therefore, this study presents a pruning structure of self-organizing HCMAC neural network to solve this problem. Experimental results show the proposed pruning structure not only can largely reduce memory requirement, but also keep fast training speed and has higher pattern classification accuracy rate than the original self-organizing HCMAC neural network does in the most testing benchmark data sets.",

author = "Chen, {Chih Ming} and Hong, {Chin Ming} and Lu, {Yung Feng}",

year = "2004",

doi = "10.1109/IJCNN.2004.1380042",

language = "English",

isbn = "0780383591",

series = "IEEE International Conference on Neural Networks - Conference Proceedings",

pages = "861--866",

booktitle = "2004 IEEE International Joint Conference on Neural Networks - Proceedings",

note = "2004 IEEE International Joint Conference on Neural Networks - Proceedings ; Conference date: 25-07-2004 Through 29-07-2004",

}

TY - GEN

T1 - A pruning structure of self-organizing HCMAC neural network classifier

AU - Chen, Chih Ming

AU - Hong, Chin Ming

AU - Lu, Yung Feng

PY - 2004

Y1 - 2004

N2 - A self-organizing HCMAC neural network was proposed to solve high dimensional pattern classification problems well in our previous work. However, a large amount of redundant GCMAC nodes might be constructed due to the expansion approach of full binary tree topology. Therefore, this study presents a pruning structure of self-organizing HCMAC neural network to solve this problem. Experimental results show the proposed pruning structure not only can largely reduce memory requirement, but also keep fast training speed and has higher pattern classification accuracy rate than the original self-organizing HCMAC neural network does in the most testing benchmark data sets.

AB - A self-organizing HCMAC neural network was proposed to solve high dimensional pattern classification problems well in our previous work. However, a large amount of redundant GCMAC nodes might be constructed due to the expansion approach of full binary tree topology. Therefore, this study presents a pruning structure of self-organizing HCMAC neural network to solve this problem. Experimental results show the proposed pruning structure not only can largely reduce memory requirement, but also keep fast training speed and has higher pattern classification accuracy rate than the original self-organizing HCMAC neural network does in the most testing benchmark data sets.

UR - http://www.scopus.com/inward/record.url?scp=10944243800&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=10944243800&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2004.1380042

DO - 10.1109/IJCNN.2004.1380042

M3 - Conference contribution

AN - SCOPUS:10944243800

SN - 0780383591

T3 - IEEE International Conference on Neural Networks - Conference Proceedings

SP - 861

EP - 866

BT - 2004 IEEE International Joint Conference on Neural Networks - Proceedings

T2 - 2004 IEEE International Joint Conference on Neural Networks - Proceedings

Y2 - 25 July 2004 through 29 July 2004

ER -

A pruning structure of self-organizing HCMAC neural network classifier

摘要

出版系列

會議

ASJC Scopus subject areas

存取文件

其它文件與鏈接

指紋

引用此