Enhancement of self organizing network elements for supervised learning

Chyon Hae Kim*, Tetsuya Ogata, Shigeki Sugano

*この研究の対応する著者

研究成果: Conference contribution

抄録

We have proposed self-organizing network elements (SONE) as a learning method for robots to meet the requirements of autonomous exploration of effective output, simple external parameters, and low calculation costs. SONE can be used as an algorithm for obtaining network topology by propagating reinforcement signals between the elements of a network. Traditionally, the analysis of fundamental features in SONE and their application to supervised learning tasks were difficult because the learning method of SONE was limited to reinforcement learning. Here the abilities of generalization, incremental learning, and temporal sequence learning were evaluated using a supervised learning method with SONE. Moreover, the proposed method enabled our SONE to be applied to a greater variety of tasks.

本文言語English
ホスト出版物のタイトル2007 IEEE International Conference on Robotics and Automation, ICRA'07
ページ92-98
ページ数7
DOI
出版ステータスPublished - 2007 11月 27
イベント2007 IEEE International Conference on Robotics and Automation, ICRA'07 - Rome, Italy
継続期間: 2007 4月 102007 4月 14

出版物シリーズ

名前Proceedings - IEEE International Conference on Robotics and Automation
ISSN(印刷版)1050-4729

Conference

Conference2007 IEEE International Conference on Robotics and Automation, ICRA'07
国/地域Italy
CityRome
Period07/4/1007/4/14

ASJC Scopus subject areas

  • ソフトウェア
  • 制御およびシステム工学
  • 人工知能
  • 電子工学および電気工学

フィンガープリント

「Enhancement of self organizing network elements for supervised learning」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