A gaussian particle swarm optimization for training a feed forward neural network

Haydee Melo, Junzo Watada

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

    Abstract

    This paper proposes a Gaussian-PSO algorithm which provides the optimized parameters for Feed Forward Neural Network. Recently the Feed Forward Neural Network is widely used in various applications as a result of its advantages such as learning capability, auto-organization and auto-adaptation. However the Neural Network has the disadvantage itself to slowly converge and get easily trapped in a local minima. In this paper, Gaussian distributed random variables are used in the PSO algorithm to enhance its performance and train the weights and bias in the Neural Network. In comparison with the Back Propagation Neural Network, the Gaussian PSO-Neural Network faster converges and is immuned to the local minima.

    Original languageEnglish
    Title of host publicationAdvances in Intelligent Systems and Computing
    PublisherSpringer Verlag
    Pages61-68
    Number of pages8
    Volume293
    ISBN (Print)9783319074757
    DOIs
    Publication statusPublished - 2014
    Event12th International Conference on Practical Applications of Agents and Multi-Agent Systems, PAAMS 2014 - Salamanca, Spain
    Duration: 2014 Jun 42014 Jun 6

    Publication series

    NameAdvances in Intelligent Systems and Computing
    Volume293
    ISSN (Print)21945357

    Other

    Other12th International Conference on Practical Applications of Agents and Multi-Agent Systems, PAAMS 2014
    CountrySpain
    CitySalamanca
    Period14/6/414/6/6

    Fingerprint

    Feedforward neural networks
    Particle swarm optimization (PSO)
    Neural networks
    Backpropagation
    Random variables

    ASJC Scopus subject areas

    • Control and Systems Engineering
    • Computer Science(all)

    Cite this

    Melo, H., & Watada, J. (2014). A gaussian particle swarm optimization for training a feed forward neural network. In Advances in Intelligent Systems and Computing (Vol. 293, pp. 61-68). (Advances in Intelligent Systems and Computing; Vol. 293). Springer Verlag. https://doi.org/10.1007/978-3-319-07476-4_8

    A gaussian particle swarm optimization for training a feed forward neural network. / Melo, Haydee; Watada, Junzo.

    Advances in Intelligent Systems and Computing. Vol. 293 Springer Verlag, 2014. p. 61-68 (Advances in Intelligent Systems and Computing; Vol. 293).

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

    Melo, H & Watada, J 2014, A gaussian particle swarm optimization for training a feed forward neural network. in Advances in Intelligent Systems and Computing. vol. 293, Advances in Intelligent Systems and Computing, vol. 293, Springer Verlag, pp. 61-68, 12th International Conference on Practical Applications of Agents and Multi-Agent Systems, PAAMS 2014, Salamanca, Spain, 14/6/4. https://doi.org/10.1007/978-3-319-07476-4_8
    Melo H, Watada J. A gaussian particle swarm optimization for training a feed forward neural network. In Advances in Intelligent Systems and Computing. Vol. 293. Springer Verlag. 2014. p. 61-68. (Advances in Intelligent Systems and Computing). https://doi.org/10.1007/978-3-319-07476-4_8
    Melo, Haydee ; Watada, Junzo. / A gaussian particle swarm optimization for training a feed forward neural network. Advances in Intelligent Systems and Computing. Vol. 293 Springer Verlag, 2014. pp. 61-68 (Advances in Intelligent Systems and Computing).
    @inproceedings{be0ef50815d2423aae30e49587a2ec7e,
    title = "A gaussian particle swarm optimization for training a feed forward neural network",
    abstract = "This paper proposes a Gaussian-PSO algorithm which provides the optimized parameters for Feed Forward Neural Network. Recently the Feed Forward Neural Network is widely used in various applications as a result of its advantages such as learning capability, auto-organization and auto-adaptation. However the Neural Network has the disadvantage itself to slowly converge and get easily trapped in a local minima. In this paper, Gaussian distributed random variables are used in the PSO algorithm to enhance its performance and train the weights and bias in the Neural Network. In comparison with the Back Propagation Neural Network, the Gaussian PSO-Neural Network faster converges and is immuned to the local minima.",
    author = "Haydee Melo and Junzo Watada",
    year = "2014",
    doi = "10.1007/978-3-319-07476-4_8",
    language = "English",
    isbn = "9783319074757",
    volume = "293",
    series = "Advances in Intelligent Systems and Computing",
    publisher = "Springer Verlag",
    pages = "61--68",
    booktitle = "Advances in Intelligent Systems and Computing",

    }

    TY - GEN

    T1 - A gaussian particle swarm optimization for training a feed forward neural network

    AU - Melo, Haydee

    AU - Watada, Junzo

    PY - 2014

    Y1 - 2014

    N2 - This paper proposes a Gaussian-PSO algorithm which provides the optimized parameters for Feed Forward Neural Network. Recently the Feed Forward Neural Network is widely used in various applications as a result of its advantages such as learning capability, auto-organization and auto-adaptation. However the Neural Network has the disadvantage itself to slowly converge and get easily trapped in a local minima. In this paper, Gaussian distributed random variables are used in the PSO algorithm to enhance its performance and train the weights and bias in the Neural Network. In comparison with the Back Propagation Neural Network, the Gaussian PSO-Neural Network faster converges and is immuned to the local minima.

    AB - This paper proposes a Gaussian-PSO algorithm which provides the optimized parameters for Feed Forward Neural Network. Recently the Feed Forward Neural Network is widely used in various applications as a result of its advantages such as learning capability, auto-organization and auto-adaptation. However the Neural Network has the disadvantage itself to slowly converge and get easily trapped in a local minima. In this paper, Gaussian distributed random variables are used in the PSO algorithm to enhance its performance and train the weights and bias in the Neural Network. In comparison with the Back Propagation Neural Network, the Gaussian PSO-Neural Network faster converges and is immuned to the local minima.

    UR - http://www.scopus.com/inward/record.url?scp=84927732782&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84927732782&partnerID=8YFLogxK

    U2 - 10.1007/978-3-319-07476-4_8

    DO - 10.1007/978-3-319-07476-4_8

    M3 - Conference contribution

    SN - 9783319074757

    VL - 293

    T3 - Advances in Intelligent Systems and Computing

    SP - 61

    EP - 68

    BT - Advances in Intelligent Systems and Computing

    PB - Springer Verlag

    ER -