Improving the self-organizing feature map algorithm using an efficient initialization scheme

淡江大學機構典藏 > 工學院 > 電機工程學系暨研究所 > 期刊論文 > Item 987654321/52821

請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/52821

題名:	Improving the self-organizing feature map algorithm using an efficient initialization scheme
作者:	蘇木春;Su, Mu-chun;劉大綱;Liu, Ta-kang;張孝德;Chang, Hsiao-te
貢獻者:	淡江大學電機工程學系
關鍵詞:	Neural Networks;Self-organizing Feature Map;Unsupervised Learning;Kohonen Algorithm
日期:	2002-03-01
上傳時間:	2010-12-01 10:35:48 (UTC+8)
出版者:	臺北縣：淡江大學
摘要:	It is often reported in the technique literature that the success of the self-organizing feature map formation is critically dependent on the initial weights and the selection of main parameters (i.e. the learning-rate parameter and the neighborhood set) of the algorithm. They usually have to be counteracted by the trial-and-error method; therefore, often time consuming retraining procedures have to precede before a neighborhood preserving feature amp is obtained. In this paper, we propose an efficient initialization scheme to construct an initial map. We then use the self-organizing feature map algorithm to make small subsequent adjustments so as to improve the accuracy of the initial map. Several data sets are tested to illustrate the performance of the proposed method.
關聯:	淡江理工學刊=Tamkang journal of science and engineering 5(1)，頁35-48
DOI:	10.6180/jase.2002.5.1.05
顯示於類別:	[電機工程學系暨研究所] 期刊論文

文件中的檔案:

檔案	大小	格式	瀏覽次數
1560-6686_5-1-5.pdf	369Kb	Adobe PDF	378	檢視/開啟

在機構典藏中所有的資料項目都受到原著作權保護.

TAIR相關文章