A New Unsupervised Neural Network for Pattern Recognition with Spiking Neurons

Lorenzo Riano, A Chella, R Rizzo

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

    3 Citations (Scopus)

    Abstract

    In this paper we propose a three-layered neural network for binary pattern recognition and memorization. Unlike the classic approach to pattern recognition, our net works organizing itself in an unsupervised way, to distinguish beetween different patterns or to recognize similar ones. If we present a binary input to the first layer, after some time steps we could read the output of the net in the third layer, as one and only one neuron activating with high firing rate; the middle layer will act as a generalization layer, i.e. similar pattern will have similar (or the same) representation in the middle layer. We used learning algorithms inspired from other works or from biological data to achieve network stability and a correct pattern memorization. The network can be used for pattern recognition or generalization by selecting output signals from the selection layer or the generalization layer.
    LanguageEnglish
    Title of host publicationUnknown Host Publication
    Number of pages6
    Publication statusPublished - Jul 2006
    EventProc. World Congress on Computational Intelligence -
    Duration: 1 Jul 2006 → …

    Conference

    ConferenceProc. World Congress on Computational Intelligence
    Period1/07/06 → …

    Fingerprint

    Neurons
    Pattern recognition
    Neural networks
    Learning algorithms

    Cite this

    Riano, L., Chella, A., & Rizzo, R. (2006). A New Unsupervised Neural Network for Pattern Recognition with Spiking Neurons. In Unknown Host Publication
    Riano, Lorenzo ; Chella, A ; Rizzo, R. / A New Unsupervised Neural Network for Pattern Recognition with Spiking Neurons. Unknown Host Publication. 2006.
    @inproceedings{2f0d40dd416f4cd5a74b2e2a3c990e6a,
    title = "A New Unsupervised Neural Network for Pattern Recognition with Spiking Neurons",
    abstract = "In this paper we propose a three-layered neural network for binary pattern recognition and memorization. Unlike the classic approach to pattern recognition, our net works organizing itself in an unsupervised way, to distinguish beetween different patterns or to recognize similar ones. If we present a binary input to the first layer, after some time steps we could read the output of the net in the third layer, as one and only one neuron activating with high firing rate; the middle layer will act as a generalization layer, i.e. similar pattern will have similar (or the same) representation in the middle layer. We used learning algorithms inspired from other works or from biological data to achieve network stability and a correct pattern memorization. The network can be used for pattern recognition or generalization by selecting output signals from the selection layer or the generalization layer.",
    author = "Lorenzo Riano and A Chella and R Rizzo",
    year = "2006",
    month = "7",
    language = "English",
    booktitle = "Unknown Host Publication",

    }

    Riano, L, Chella, A & Rizzo, R 2006, A New Unsupervised Neural Network for Pattern Recognition with Spiking Neurons. in Unknown Host Publication. Proc. World Congress on Computational Intelligence, 1/07/06.

    A New Unsupervised Neural Network for Pattern Recognition with Spiking Neurons. / Riano, Lorenzo; Chella, A; Rizzo, R.

    Unknown Host Publication. 2006.

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

    TY - GEN

    T1 - A New Unsupervised Neural Network for Pattern Recognition with Spiking Neurons

    AU - Riano, Lorenzo

    AU - Chella, A

    AU - Rizzo, R

    PY - 2006/7

    Y1 - 2006/7

    N2 - In this paper we propose a three-layered neural network for binary pattern recognition and memorization. Unlike the classic approach to pattern recognition, our net works organizing itself in an unsupervised way, to distinguish beetween different patterns or to recognize similar ones. If we present a binary input to the first layer, after some time steps we could read the output of the net in the third layer, as one and only one neuron activating with high firing rate; the middle layer will act as a generalization layer, i.e. similar pattern will have similar (or the same) representation in the middle layer. We used learning algorithms inspired from other works or from biological data to achieve network stability and a correct pattern memorization. The network can be used for pattern recognition or generalization by selecting output signals from the selection layer or the generalization layer.

    AB - In this paper we propose a three-layered neural network for binary pattern recognition and memorization. Unlike the classic approach to pattern recognition, our net works organizing itself in an unsupervised way, to distinguish beetween different patterns or to recognize similar ones. If we present a binary input to the first layer, after some time steps we could read the output of the net in the third layer, as one and only one neuron activating with high firing rate; the middle layer will act as a generalization layer, i.e. similar pattern will have similar (or the same) representation in the middle layer. We used learning algorithms inspired from other works or from biological data to achieve network stability and a correct pattern memorization. The network can be used for pattern recognition or generalization by selecting output signals from the selection layer or the generalization layer.

    M3 - Conference contribution

    BT - Unknown Host Publication

    ER -

    Riano L, Chella A, Rizzo R. A New Unsupervised Neural Network for Pattern Recognition with Spiking Neurons. In Unknown Host Publication. 2006