電気学会論文誌C(電子・情報・システム部門誌)
Online ISSN : 1348-8155
Print ISSN : 0385-4221
ISSN-L : 0385-4221
論文
部分空間の等入力に基づく生成的競合学習
前田 道治宮島 廣美
著者情報
ジャーナル フリー

2003 年 123 巻 3 号 p. 560-567

詳細
抄録
In this paper, we exhibit that partition errors are equivalent to each other when the numbers of inputs in a partition space are mutually equal, and describe that the average distortion is asymptotically minimized. According to the equinumber principle, a creation method of competitive learning is proposed with the objective of avoiding the initial dependency of reference vectors. The present approach which has output units without neighboring relations equalizes the numbers of inputs in a partition space. To begin with, only one output unit is prepared at the initial stage, and a reference vector, according to the unit, is updated under competitive learning. Then output units are created sequentially to reach a prespecified number of neurons based on the equinumber principle, and competitive learning occurs until the termination condition is satisfied. Experimental results show the effectiveness of the present technique in the average distortion. Furthermore the present approach is applied to image data and the validity in employing as an image coding system is examined.
著者関連情報
© 電気学会 2003
前の記事 次の記事
feedback
Top