Please use this identifier to cite or link to this item:
標題: An Efficient Initialization Scheme for SOM Algorithm Based on Reference Point and Filters
作者: Shieh, S.L.
Liao, I.E.
Hwang, K.F.
Chen, H.Y.
關鍵字: clustering methods;self-organizing map;unsupervised learning;reference point;filters;organizing feature map;neural networks
Project: Ieice Transactions on Information and Systems
期刊/報告no:: Ieice Transactions on Information and Systems, Volume E92D, Issue 3, Page(s) 422-432.
This paper proposes an efficient self-organizing map algorithm based on reference point and filters. A strategy, called Reference Point SOM (RPSOM) is proposed to improve SOM execution time by means of filtering with two thresholds T(1) and T(2). We use one threshold. T(1), to define the search boundary parameter used to search for the Best-Matching, Unit (BMU) with respect to input vectors. The other threshold, T(2) is used as the search boundary within which the BMU finds its neighbors. The proposed algorithm reduces the time complexity from O(n(2)) to O(n) in finding, the initial neurons as compared to the algorithm, proposed by Su et al. [16]. The RPSOM dramatically reduces the time complexity, especially in the computation of large data set. Front the experimental results, we find that it is better to construct a good initial map and then to use the unsupervised learning to make small subsequent adjustments.
ISSN: 0916-8532
DOI: 10.1587/transinf.E92.D.422
Appears in Collections:資訊科學與工程學系所

Show full item record

Google ScholarTM




Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.