Position-based competition learning of neural-networks array

R. Saegusa, P. Hartono, S. Hashimoto

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

    Abstract

    In this paper, we propose a model of neural-network array composed of a number of MLPs (members), in which each member can be automatically trained to recognize the different dynamics of time series data. The proposed array adopts a position-based competitive learning methods that puts members with similar dynamics close to each other. The proposed array model intends to deal effectively with switching dynamics problems and produce a map of the dynamics.

    Original languageEnglish
    Title of host publicationProceedings of the International Joint Conference on Neural Networks
    Pages2817-2820
    Number of pages4
    Volume4
    Publication statusPublished - 2001
    EventInternational Joint Conference on Neural Networks (IJCNN'01) - Washington, DC
    Duration: 2001 Jul 152001 Jul 19

    Other

    OtherInternational Joint Conference on Neural Networks (IJCNN'01)
    CityWashington, DC
    Period01/7/1501/7/19

    Fingerprint

    Neural networks
    Time series

    ASJC Scopus subject areas

    • Software

    Cite this

    Saegusa, R., Hartono, P., & Hashimoto, S. (2001). Position-based competition learning of neural-networks array. In Proceedings of the International Joint Conference on Neural Networks (Vol. 4, pp. 2817-2820)

    Position-based competition learning of neural-networks array. / Saegusa, R.; Hartono, P.; Hashimoto, S.

    Proceedings of the International Joint Conference on Neural Networks. Vol. 4 2001. p. 2817-2820.

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

    Saegusa, R, Hartono, P & Hashimoto, S 2001, Position-based competition learning of neural-networks array. in Proceedings of the International Joint Conference on Neural Networks. vol. 4, pp. 2817-2820, International Joint Conference on Neural Networks (IJCNN'01), Washington, DC, 01/7/15.
    Saegusa R, Hartono P, Hashimoto S. Position-based competition learning of neural-networks array. In Proceedings of the International Joint Conference on Neural Networks. Vol. 4. 2001. p. 2817-2820
    Saegusa, R. ; Hartono, P. ; Hashimoto, S. / Position-based competition learning of neural-networks array. Proceedings of the International Joint Conference on Neural Networks. Vol. 4 2001. pp. 2817-2820
    @inproceedings{0580b76a27054ac1bcf6c3cbbca0d02e,
    title = "Position-based competition learning of neural-networks array",
    abstract = "In this paper, we propose a model of neural-network array composed of a number of MLPs (members), in which each member can be automatically trained to recognize the different dynamics of time series data. The proposed array adopts a position-based competitive learning methods that puts members with similar dynamics close to each other. The proposed array model intends to deal effectively with switching dynamics problems and produce a map of the dynamics.",
    author = "R. Saegusa and P. Hartono and S. Hashimoto",
    year = "2001",
    language = "English",
    volume = "4",
    pages = "2817--2820",
    booktitle = "Proceedings of the International Joint Conference on Neural Networks",

    }

    TY - GEN

    T1 - Position-based competition learning of neural-networks array

    AU - Saegusa, R.

    AU - Hartono, P.

    AU - Hashimoto, S.

    PY - 2001

    Y1 - 2001

    N2 - In this paper, we propose a model of neural-network array composed of a number of MLPs (members), in which each member can be automatically trained to recognize the different dynamics of time series data. The proposed array adopts a position-based competitive learning methods that puts members with similar dynamics close to each other. The proposed array model intends to deal effectively with switching dynamics problems and produce a map of the dynamics.

    AB - In this paper, we propose a model of neural-network array composed of a number of MLPs (members), in which each member can be automatically trained to recognize the different dynamics of time series data. The proposed array adopts a position-based competitive learning methods that puts members with similar dynamics close to each other. The proposed array model intends to deal effectively with switching dynamics problems and produce a map of the dynamics.

    UR - http://www.scopus.com/inward/record.url?scp=0034850385&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0034850385&partnerID=8YFLogxK

    M3 - Conference contribution

    VL - 4

    SP - 2817

    EP - 2820

    BT - Proceedings of the International Joint Conference on Neural Networks

    ER -