WEKO3
アイテム
Modular Network SOM (mnSOM): From Vector Space to Function Space
http://hdl.handle.net/10228/2366
http://hdl.handle.net/10228/2366b1829cbd-35cb-4ff4-ae8c-62f1491da582
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
IJCNN.2005.1556114.pdf (758.0 kB)
|
|
| アイテムタイプ | 会議発表論文 = Conference Paper(1) | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2009-04-10 | |||||||||||
| 資源タイプ | ||||||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_5794 | |||||||||||
| 資源タイプ | conference paper | |||||||||||
| タイトル | ||||||||||||
| タイトル | Modular Network SOM (mnSOM): From Vector Space to Function Space | |||||||||||
| 言語 | en | |||||||||||
| 言語 | ||||||||||||
| 言語 | eng | |||||||||||
| 著者 |
古川, 徹生
× 古川, 徹生
WEKO
661
× Tokunaga, Kazuhiro× Morishita, Kenji× Yasui, Syozo |
|||||||||||
| 抄録 | ||||||||||||
| 内容記述タイプ | Abstract | |||||||||||
| 内容記述 | Kohonen's Self-Organizing Map (SOM), which performs topology-preserving transformation from a highdimensional data vector space to a low-dimensional map space, provides a powerful tool for data analysis, classification and visualization in many application fields. Despite its powerfulness, SOM can only deal with vectorized data, although many expansions have been proposed for various data-type cases. This study aims to develop a novel generalization of SOM called modular Iletwork SOM (mIlSOM), which enables users to deal with general data classes in a consistent manner. mnSOM has an array structure consisting of function modules that are trainable neural networks, e.g. multi-layer perceptrons (MLPs), instead of the vector units of the conventional SOM family. In the case of MLPmodules, mnSOM learns a group of systems or functions in terms of the input-output relationships, and at the same time mnSOM generates a feature map that shows distances between the learned systems. Thus, mnSOM with MLP modules is an SOM in function space rather than in vector space. From this point of view, the conventional SOM of Kohonen's can be regarded as a special case of mnSOM, the modules consisting of fixed-value bias units. In this paper, mnSOM with MLP modules is described along with some application examples. | |||||||||||
| 言語 | en | |||||||||||
| 備考 | ||||||||||||
| 内容記述タイプ | Other | |||||||||||
| 内容記述 | 2005 IEEE International Joint Conference on Neural Networks, 31 July - 4 August, 2005, Montreal, Québec, Canada | |||||||||||
| 書誌情報 |
en : Proceedings of International Joint Conference on Neural Networks 巻 3, p. 1581-1586, 発行日 2005-08-02 |
|||||||||||
| 出版社 | ||||||||||||
| 出版社 | IEEE | |||||||||||
| DOI | ||||||||||||
| 関連タイプ | isIdenticalTo | |||||||||||
| 識別子タイプ | DOI | |||||||||||
| 関連識別子 | https://doi.org/10.1109/IJCNN.2005.1556114 | |||||||||||
| ISBN | ||||||||||||
| 識別子タイプ | ISBN | |||||||||||
| 関連識別子 | 0-7803-9048-2 | |||||||||||
| ISSN | ||||||||||||
| 収録物識別子タイプ | EISSN | |||||||||||
| 収録物識別子 | 2161-4407 | |||||||||||
| ISSN | ||||||||||||
| 収録物識別子タイプ | PISSN | |||||||||||
| 収録物識別子 | 2161-4393 | |||||||||||
| 著作権関連情報 | ||||||||||||
| 権利情報 | ©2008 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. | |||||||||||
| 出版タイプ | ||||||||||||
| 出版タイプ | VoR | |||||||||||
| 出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||||||||
| 査読の有無 | ||||||||||||
| 値 | yes | |||||||||||
