Preliminary evaluation of batch-learning self-organizing map algorithm on a graphic processor

Akihiro Shitara, Yuri Nishikawa, Masato Yoshimi, Takashi Abe, Toshimichi Ikemura, Hideharu Amano

研究成果: Conference contribution

抄録

In this paper, we introduce a GPU implementation and evaluation of batch learning self-organizing maps (BL-SOM) algorithm, which improves Kohonen's original SOM algorithm by making input data sequence independent from learning process. We used CUDA provided by NVIDIA Corporation for parallel programming, profiling, and data flow optimization so as to exploit inherent datalevel parallelism of the algorithm. With various parameter combinations, implementation on GTX280 achieved 250 times higher performance compared to Intel's Core2Quad Q6600 2.40GHz when parameters of map size, dimension of vectors, learning size and iteration of learning were 960×960, 136, 70 and 1, respectively.

本文言語English
ホスト出版物のタイトルProceedings of the 9th IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2010
出版社Acta Press
ページ96-104
ページ数9
ISBN(印刷版)9780889868205
DOI
出版ステータスPublished - 2010
イベント9th IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2010 - Innsbruck, Austria
継続期間: 2010 2月 162010 2月 18

出版物シリーズ

名前Proceedings of the 9th IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2010

Other

Other9th IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2010
国/地域Austria
CityInnsbruck
Period10/2/1610/2/18

ASJC Scopus subject areas

  • 計算理論と計算数学
  • コンピュータ ネットワークおよび通信
  • ソフトウェア

フィンガープリント

「Preliminary evaluation of batch-learning self-organizing map algorithm on a graphic processor」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル