Efficient organization of network topology based on reinforcement signals

Chyon Hae Kim, Shigeki Sugano, Tetsuya Ogata

    Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

    Abstract

    We developed a learning system for autonomous robots that allows for autonomous exploration of the effective output, and has simple external parameters and a low calculation cost. We propose the concept of self-organizing network elements (SONE) for creating learning systems with these characteristics. We created and evaluated a self-organizing logic circuit by using this concept. Our results indicated this learning system had the characteristics.

    Original languageEnglish
    Title of host publicationIEEE International Conference on Intelligent Robots and Systems
    Pages3154-3159
    Number of pages6
    DOIs
    Publication statusPublished - 2006
    Event2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2006 - Beijing
    Duration: 2006 Oct 9 → 2006 Oct 15

    Other

    Other2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2006
    CityBeijing
    Period06/10/9 → 06/10/15

    Fingerprint

    Learning systems
    Reinforcement
    Topology
    Logic circuits
    Robots
    Costs

    ASJC Scopus subject areas

    • Control and Systems Engineering

    Cite this

    Kim, C. H., Sugano, S., & Ogata, T. (2006). Efficient organization of network topology based on reinforcement signals. In IEEE International Conference on Intelligent Robots and Systems (pp. 3154-3159). [4058881] https://doi.org/10.1109/IROS.2006.282338

    Efficient organization of network topology based on reinforcement signals. / Kim, Chyon Hae; Sugano, Shigeki; Ogata, Tetsuya.

    IEEE International Conference on Intelligent Robots and Systems. 2006. p. 3154-3159 4058881.

    Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

    Kim, CH, Sugano, S & Ogata, T 2006, Efficient organization of network topology based on reinforcement signals. in IEEE International Conference on Intelligent Robots and Systems., 4058881, pp. 3154-3159, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2006, Beijing, 06/10/9. https://doi.org/10.1109/IROS.2006.282338
    Kim CH, Sugano S, Ogata T. Efficient organization of network topology based on reinforcement signals. In IEEE International Conference on Intelligent Robots and Systems. 2006. p. 3154-3159. 4058881 https://doi.org/10.1109/IROS.2006.282338
    Kim, Chyon Hae ; Sugano, Shigeki ; Ogata, Tetsuya. / Efficient organization of network topology based on reinforcement signals. IEEE International Conference on Intelligent Robots and Systems. 2006. pp. 3154-3159
    @inproceedings{80c2eec5548947a897aa4105c9b17e9c,
    title = "Efficient organization of network topology based on reinforcement signals",
    abstract = "We developed a learning system for autonomous robots that allows for autonomous exploration of the effective output, and has simple external parameters and a low calculation cost. We propose the concept of self-organizing network elements (SONE) for creating learning systems with these characteristics. We created and evaluated a self-organizing logic circuit by using this concept. Our results indicated this learning system had the characteristics.",
    author = "Kim, {Chyon Hae} and Shigeki Sugano and Tetsuya Ogata",
    year = "2006",
    doi = "10.1109/IROS.2006.282338",
    language = "English",
    isbn = "142440259X",
    pages = "3154--3159",
    booktitle = "IEEE International Conference on Intelligent Robots and Systems",

    }

    TY - GEN

    T1 - Efficient organization of network topology based on reinforcement signals

    AU - Kim, Chyon Hae

    AU - Sugano, Shigeki

    AU - Ogata, Tetsuya

    PY - 2006

    Y1 - 2006

    N2 - We developed a learning system for autonomous robots that allows for autonomous exploration of the effective output, and has simple external parameters and a low calculation cost. We propose the concept of self-organizing network elements (SONE) for creating learning systems with these characteristics. We created and evaluated a self-organizing logic circuit by using this concept. Our results indicated this learning system had the characteristics.

    AB - We developed a learning system for autonomous robots that allows for autonomous exploration of the effective output, and has simple external parameters and a low calculation cost. We propose the concept of self-organizing network elements (SONE) for creating learning systems with these characteristics. We created and evaluated a self-organizing logic circuit by using this concept. Our results indicated this learning system had the characteristics.

    UR - http://www.scopus.com/inward/record.url?scp=34250674781&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=34250674781&partnerID=8YFLogxK

    U2 - 10.1109/IROS.2006.282338

    DO - 10.1109/IROS.2006.282338

    M3 - Conference contribution

    AN - SCOPUS:34250674781

    SN - 142440259X

    SN - 9781424402595

    SP - 3154

    EP - 3159

    BT - IEEE International Conference on Intelligent Robots and Systems

    ER -

    Access to Document