Template design for cellular nonlinear networks with 1-bit weights

M. Laiho, A. Paasio, Jacek Flak, K. A. I. Halonen

    Research output: Contribution to journalArticleScientificpeer-review

    16 Citations (Scopus)

    Abstract

    In this paper, we show how a cellular nonlinear network with 1-bit weight programmability can be used for processing black and white image data. When using such a binary-programmable network, some templates need to be processed algorithmically, in other words, divided into subtasks that are processed consecutively. We classify templates into groups based on their properties and give guidelines as to how the division into subtasks (when applicable) is performed. A large collection of templates suitable for the proposed model is shown. We also describe one possible cell structure that realizes the binary-programmable model. The cell is modeled with Matlab and selected template simulations are shown.
    Original languageEnglish
    Pages (from-to)904 - 913
    Number of pages10
    JournalIEEE Transactions on Circuits and Systems I: Regular Papers
    Volume55
    Issue number3
    DOIs
    Publication statusPublished - 2008
    MoE publication typeA1 Journal article-refereed

    Fingerprint

    Nonlinear networks
    Processing

    Keywords

    • Analog processing circuits
    • Cellular neural networks (CNNs)
    • Image processing
    • Parallel architectures
    • Threshold logic

    Cite this

    @article{ff7e96b36373410fa1213eb198f583f2,
    title = "Template design for cellular nonlinear networks with 1-bit weights",
    abstract = "In this paper, we show how a cellular nonlinear network with 1-bit weight programmability can be used for processing black and white image data. When using such a binary-programmable network, some templates need to be processed algorithmically, in other words, divided into subtasks that are processed consecutively. We classify templates into groups based on their properties and give guidelines as to how the division into subtasks (when applicable) is performed. A large collection of templates suitable for the proposed model is shown. We also describe one possible cell structure that realizes the binary-programmable model. The cell is modeled with Matlab and selected template simulations are shown.",
    keywords = "Analog processing circuits, Cellular neural networks (CNNs), Image processing, Parallel architectures, Threshold logic",
    author = "M. Laiho and A. Paasio and Jacek Flak and Halonen, {K. A. I.}",
    year = "2008",
    doi = "10.1109/TCSI.2008.916438",
    language = "English",
    volume = "55",
    pages = "904 -- 913",
    journal = "IEEE Transactions on Circuits and Systems I: Regular Papers",
    issn = "1549-8328",
    publisher = "IEEE Institute of Electrical and Electronic Engineers",
    number = "3",

    }

    Template design for cellular nonlinear networks with 1-bit weights. / Laiho, M.; Paasio, A.; Flak, Jacek; Halonen, K. A. I.

    In: IEEE Transactions on Circuits and Systems I: Regular Papers, Vol. 55, No. 3, 2008, p. 904 - 913.

    Research output: Contribution to journalArticleScientificpeer-review

    TY - JOUR

    T1 - Template design for cellular nonlinear networks with 1-bit weights

    AU - Laiho, M.

    AU - Paasio, A.

    AU - Flak, Jacek

    AU - Halonen, K. A. I.

    PY - 2008

    Y1 - 2008

    N2 - In this paper, we show how a cellular nonlinear network with 1-bit weight programmability can be used for processing black and white image data. When using such a binary-programmable network, some templates need to be processed algorithmically, in other words, divided into subtasks that are processed consecutively. We classify templates into groups based on their properties and give guidelines as to how the division into subtasks (when applicable) is performed. A large collection of templates suitable for the proposed model is shown. We also describe one possible cell structure that realizes the binary-programmable model. The cell is modeled with Matlab and selected template simulations are shown.

    AB - In this paper, we show how a cellular nonlinear network with 1-bit weight programmability can be used for processing black and white image data. When using such a binary-programmable network, some templates need to be processed algorithmically, in other words, divided into subtasks that are processed consecutively. We classify templates into groups based on their properties and give guidelines as to how the division into subtasks (when applicable) is performed. A large collection of templates suitable for the proposed model is shown. We also describe one possible cell structure that realizes the binary-programmable model. The cell is modeled with Matlab and selected template simulations are shown.

    KW - Analog processing circuits

    KW - Cellular neural networks (CNNs)

    KW - Image processing

    KW - Parallel architectures

    KW - Threshold logic

    U2 - 10.1109/TCSI.2008.916438

    DO - 10.1109/TCSI.2008.916438

    M3 - Article

    VL - 55

    SP - 904

    EP - 913

    JO - IEEE Transactions on Circuits and Systems I: Regular Papers

    JF - IEEE Transactions on Circuits and Systems I: Regular Papers

    SN - 1549-8328

    IS - 3

    ER -