Effective learning in noisy environment using neural network ensemble

Pitoyo Hartono, Shuji Hashimoto

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

    1 Citation (Scopus)

    Abstract

    We have previously proposed a model of neural network ensemble composed of a number of Multi Layer Perceptrons (MLP). The ensemble is trained so that each member has a unique expertise. It is also provided with a mechanism to automatically select the most relevant member with respect to the given environment, enabling the ensemble to adapt effectively in changing environment. In this research we trained the ensemble with noisy training data set, which is a training set that contains a particular percentage of contradictionary (false) data. Based on the members' expertise the ensemble has the ability to distinguish contradictionary data and treat such kind of data set as one unique environment that differs from the clean environment formed by correct data. In the training process the ensemble will automatically select one of its member to be trained in the clean environment and switch to another member whenever a contradictionary data is given, resulting that one of the ensemble member will be successfully adapting the clean environment.

    Original languageEnglish
    Title of host publicationProceedings of the International Joint Conference on Neural Networks
    Place of PublicationPiscataway, NJ, United States
    PublisherIEEE
    Pages179-184
    Number of pages6
    Volume2
    Publication statusPublished - 2000
    EventInternational Joint Conference on Neural Networks (IJCNN'2000) - Como, Italy
    Duration: 2000 Jul 242000 Jul 27

    Other

    OtherInternational Joint Conference on Neural Networks (IJCNN'2000)
    CityComo, Italy
    Period00/7/2400/7/27

    Fingerprint

    Multilayer neural networks
    Switches
    Neural networks

    ASJC Scopus subject areas

    • Software

    Cite this

    Hartono, P., & Hashimoto, S. (2000). Effective learning in noisy environment using neural network ensemble. In Proceedings of the International Joint Conference on Neural Networks (Vol. 2, pp. 179-184). Piscataway, NJ, United States: IEEE.

    Effective learning in noisy environment using neural network ensemble. / Hartono, Pitoyo; Hashimoto, Shuji.

    Proceedings of the International Joint Conference on Neural Networks. Vol. 2 Piscataway, NJ, United States : IEEE, 2000. p. 179-184.

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

    Hartono, P & Hashimoto, S 2000, Effective learning in noisy environment using neural network ensemble. in Proceedings of the International Joint Conference on Neural Networks. vol. 2, IEEE, Piscataway, NJ, United States, pp. 179-184, International Joint Conference on Neural Networks (IJCNN'2000), Como, Italy, 00/7/24.
    Hartono P, Hashimoto S. Effective learning in noisy environment using neural network ensemble. In Proceedings of the International Joint Conference on Neural Networks. Vol. 2. Piscataway, NJ, United States: IEEE. 2000. p. 179-184
    Hartono, Pitoyo ; Hashimoto, Shuji. / Effective learning in noisy environment using neural network ensemble. Proceedings of the International Joint Conference on Neural Networks. Vol. 2 Piscataway, NJ, United States : IEEE, 2000. pp. 179-184
    @inproceedings{7780267be2994e91bd69d5b854237420,
    title = "Effective learning in noisy environment using neural network ensemble",
    abstract = "We have previously proposed a model of neural network ensemble composed of a number of Multi Layer Perceptrons (MLP). The ensemble is trained so that each member has a unique expertise. It is also provided with a mechanism to automatically select the most relevant member with respect to the given environment, enabling the ensemble to adapt effectively in changing environment. In this research we trained the ensemble with noisy training data set, which is a training set that contains a particular percentage of contradictionary (false) data. Based on the members' expertise the ensemble has the ability to distinguish contradictionary data and treat such kind of data set as one unique environment that differs from the clean environment formed by correct data. In the training process the ensemble will automatically select one of its member to be trained in the clean environment and switch to another member whenever a contradictionary data is given, resulting that one of the ensemble member will be successfully adapting the clean environment.",
    author = "Pitoyo Hartono and Shuji Hashimoto",
    year = "2000",
    language = "English",
    volume = "2",
    pages = "179--184",
    booktitle = "Proceedings of the International Joint Conference on Neural Networks",
    publisher = "IEEE",

    }

    TY - GEN

    T1 - Effective learning in noisy environment using neural network ensemble

    AU - Hartono, Pitoyo

    AU - Hashimoto, Shuji

    PY - 2000

    Y1 - 2000

    N2 - We have previously proposed a model of neural network ensemble composed of a number of Multi Layer Perceptrons (MLP). The ensemble is trained so that each member has a unique expertise. It is also provided with a mechanism to automatically select the most relevant member with respect to the given environment, enabling the ensemble to adapt effectively in changing environment. In this research we trained the ensemble with noisy training data set, which is a training set that contains a particular percentage of contradictionary (false) data. Based on the members' expertise the ensemble has the ability to distinguish contradictionary data and treat such kind of data set as one unique environment that differs from the clean environment formed by correct data. In the training process the ensemble will automatically select one of its member to be trained in the clean environment and switch to another member whenever a contradictionary data is given, resulting that one of the ensemble member will be successfully adapting the clean environment.

    AB - We have previously proposed a model of neural network ensemble composed of a number of Multi Layer Perceptrons (MLP). The ensemble is trained so that each member has a unique expertise. It is also provided with a mechanism to automatically select the most relevant member with respect to the given environment, enabling the ensemble to adapt effectively in changing environment. In this research we trained the ensemble with noisy training data set, which is a training set that contains a particular percentage of contradictionary (false) data. Based on the members' expertise the ensemble has the ability to distinguish contradictionary data and treat such kind of data set as one unique environment that differs from the clean environment formed by correct data. In the training process the ensemble will automatically select one of its member to be trained in the clean environment and switch to another member whenever a contradictionary data is given, resulting that one of the ensemble member will be successfully adapting the clean environment.

    UR - http://www.scopus.com/inward/record.url?scp=0033717380&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0033717380&partnerID=8YFLogxK

    M3 - Conference contribution

    VL - 2

    SP - 179

    EP - 184

    BT - Proceedings of the International Joint Conference on Neural Networks

    PB - IEEE

    CY - Piscataway, NJ, United States

    ER -