Enhancement of self organizing network elements for supervised learning

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    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.

    Original languageEnglish
    Title of host publicationProceedings - IEEE International Conference on Robotics and Automation
    Pages92-98
    Number of pages7
    DOIs
    Publication statusPublished - 2007
    Event2007 IEEE International Conference on Robotics and Automation, ICRA'07 - Rome
    Duration: 2007 Apr 102007 Apr 14

    Other

    Other2007 IEEE International Conference on Robotics and Automation, ICRA'07
    CityRome
    Period07/4/1007/4/14

    Fingerprint

    Supervised learning
    Reinforcement learning
    Reinforcement
    Topology
    Robots
    Costs

    ASJC Scopus subject areas

    • Software
    • Control and Systems Engineering

    Cite this

    Kim, C. H., Ogata, T., & Sugano, S. (2007). Enhancement of self organizing network elements for supervised learning. In Proceedings - IEEE International Conference on Robotics and Automation (pp. 92-98). [4209075] https://doi.org/10.1109/ROBOT.2007.363770

    Enhancement of self organizing network elements for supervised learning. / Kim, Chyon Hae; Ogata, Tetsuya; Sugano, Shigeki.

    Proceedings - IEEE International Conference on Robotics and Automation. 2007. p. 92-98 4209075.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Kim, CH, Ogata, T & Sugano, S 2007, Enhancement of self organizing network elements for supervised learning. in Proceedings - IEEE International Conference on Robotics and Automation., 4209075, pp. 92-98, 2007 IEEE International Conference on Robotics and Automation, ICRA'07, Rome, 07/4/10. https://doi.org/10.1109/ROBOT.2007.363770
    Kim CH, Ogata T, Sugano S. Enhancement of self organizing network elements for supervised learning. In Proceedings - IEEE International Conference on Robotics and Automation. 2007. p. 92-98. 4209075 https://doi.org/10.1109/ROBOT.2007.363770
    Kim, Chyon Hae ; Ogata, Tetsuya ; Sugano, Shigeki. / Enhancement of self organizing network elements for supervised learning. Proceedings - IEEE International Conference on Robotics and Automation. 2007. pp. 92-98
    @inproceedings{c9ca92b140af407c88ca2d85bcbc9f22,
    title = "Enhancement of self organizing network elements for supervised learning",
    abstract = "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.",
    author = "Kim, {Chyon Hae} and Tetsuya Ogata and Shigeki Sugano",
    year = "2007",
    doi = "10.1109/ROBOT.2007.363770",
    language = "English",
    isbn = "1424406021",
    pages = "92--98",
    booktitle = "Proceedings - IEEE International Conference on Robotics and Automation",

    }

    TY - GEN

    T1 - Enhancement of self organizing network elements for supervised learning

    AU - Kim, Chyon Hae

    AU - Ogata, Tetsuya

    AU - Sugano, Shigeki

    PY - 2007

    Y1 - 2007

    N2 - 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.

    AB - 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.

    UR - http://www.scopus.com/inward/record.url?scp=36348955070&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=36348955070&partnerID=8YFLogxK

    U2 - 10.1109/ROBOT.2007.363770

    DO - 10.1109/ROBOT.2007.363770

    M3 - Conference contribution

    AN - SCOPUS:36348955070

    SN - 1424406021

    SN - 9781424406029

    SP - 92

    EP - 98

    BT - Proceedings - IEEE International Conference on Robotics and Automation

    ER -