Spherical SOM and Arrangement of Neurons Using Helix on Sphere

• Item type: Trans(1)
• 公開日: 2006-02-15
• タイトル: Spherical SOM and Arrangement of Neurons Using Helix on Sphere
• タイトル / 言語: en
• タイトル: Spherical SOM and Arrangement of Neurons Using Helix on Sphere
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: 自己組織化マップ
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_6501
• 資源タイプ: journal article
• 著者所属: Nara Institute of Science and Technology Graduate School of Information Science
• 著者所属: Nara Institute of Science and Technology Graduate School of Information Science
• 著者所属: Nara Institute of Science and Technology Graduate School of Information Science
• 著者所属: Nara Institu
• 著者所属(英): en
• 著者所属(英): Nara Institute of Science and Technology Graduate School of Information Science
• 著者所属(英): en
• 著者所属(英): Nara Institute of Science and Technology Graduate School of Information Science
• 著者所属(英): en
• 著者所属(英): Nara Institute of Science and Technology Graduate School of Information Science
• 著者所属(英): en
• 著者所属(英): Nara Institute of Science and Technology Graduate School of Information Science
• 著者名: Hirokazu, Nishio; Md.Altaf-Ul-Amin; Ken, Kurokawa; Shigehiko, Kanaya
• 著者名(英): Hirokazu, Nishio; Md., Altaf-Ul-Amin; Ken, Kurokawa; Shigehiko, Kanaya
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Self-organizing maps (SOM) are a kind of neural network and are applied to many fields. In many applications there are borders surrounding the neuron arrangement. It causes a problem which is called ‘Border effect’ because the number of neighborhood neurons of a neuron near a border is different from that of a neuron near the center. This problem can be solved by arranging neurons uniformly on the surface of a sphere. But by the conventional method we cannot arrange neurons of arbitrary number. Therefore it is inconvenient to use. Here we developed a method to arrange the neurons of arbitrary number by dividing a helix which covers the surface of a sphere into equal parts. It also can arrange neurons on a sphere more uniformly than the conventional method.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Self-organizing maps (SOM) are a kind of neural network, and are applied to many fields. In many applications, there are borders surrounding the neuron arrangement. It causes a problem which is called ‘Border effect’ because the number of neighborhood neurons of a neuron near a border is different from that of a neuron near the center. This problem can be solved by arranging neurons uniformly on the surface of a sphere. But by the conventional method we cannot arrange neurons of arbitrary number. Therefore, it is inconvenient to use. Here we developed a method to arrange the neurons of arbitrary number by dividing a helix which covers the surface of a sphere into equal parts. It also can arrange neurons on a sphere more uniformly than the conventional method.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA11464803
• 書誌情報: 情報処理学会論文誌数理モデル化と応用（TOM）; 巻 47, 号 SIG1(TOM14), p. 56-60, 発行日 2006-02-15
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 1882-7780
• 出版者 / 言語: ja
• 出版者: 情報処理学会