Hash-coding in CMAC neural networks

Zi Qin Wang, Jeffrey Louis Schiano, Mark Ginsberg

    Research output: Contribution to conferencePaper

    26 Citations (Scopus)

    Abstract

    Hash-coding is used in CMAC neural networks to reduce the required memory, thereby making the CMAC practical to implement. In this paper the original motivation and rationale for using hash-coding in CMAC [1] are questioned and it is shown that, contrary to the traditional believe, that hash-coding is unable to enhance CMAC's approximation ability. A comparison between the CMAC performance obtained with two popular hash-coding methods is given.

    Original languageEnglish (US)
    Pages1698-1703
    Number of pages6
    StatePublished - Jan 1 1996
    EventProceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4) - Washington, DC, USA
    Duration: Jun 3 1996Jun 6 1996

    Other

    OtherProceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4)
    CityWashington, DC, USA
    Period6/3/966/6/96

    Fingerprint

    Neural networks
    Data storage equipment

    All Science Journal Classification (ASJC) codes

    • Software

    Cite this

    Wang, Z. Q., Schiano, J. L., & Ginsberg, M. (1996). Hash-coding in CMAC neural networks. 1698-1703. Paper presented at Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, .
    Wang, Zi Qin ; Schiano, Jeffrey Louis ; Ginsberg, Mark. / Hash-coding in CMAC neural networks. Paper presented at Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, .6 p.
    @conference{0eb8280591434709bd324b2cb96f639c,
    title = "Hash-coding in CMAC neural networks",
    abstract = "Hash-coding is used in CMAC neural networks to reduce the required memory, thereby making the CMAC practical to implement. In this paper the original motivation and rationale for using hash-coding in CMAC [1] are questioned and it is shown that, contrary to the traditional believe, that hash-coding is unable to enhance CMAC's approximation ability. A comparison between the CMAC performance obtained with two popular hash-coding methods is given.",
    author = "Wang, {Zi Qin} and Schiano, {Jeffrey Louis} and Mark Ginsberg",
    year = "1996",
    month = "1",
    day = "1",
    language = "English (US)",
    pages = "1698--1703",
    note = "Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4) ; Conference date: 03-06-1996 Through 06-06-1996",

    }

    Wang, ZQ, Schiano, JL & Ginsberg, M 1996, 'Hash-coding in CMAC neural networks', Paper presented at Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, 6/3/96 - 6/6/96 pp. 1698-1703.

    Hash-coding in CMAC neural networks. / Wang, Zi Qin; Schiano, Jeffrey Louis; Ginsberg, Mark.

    1996. 1698-1703 Paper presented at Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, .

    Research output: Contribution to conferencePaper

    TY - CONF

    T1 - Hash-coding in CMAC neural networks

    AU - Wang, Zi Qin

    AU - Schiano, Jeffrey Louis

    AU - Ginsberg, Mark

    PY - 1996/1/1

    Y1 - 1996/1/1

    N2 - Hash-coding is used in CMAC neural networks to reduce the required memory, thereby making the CMAC practical to implement. In this paper the original motivation and rationale for using hash-coding in CMAC [1] are questioned and it is shown that, contrary to the traditional believe, that hash-coding is unable to enhance CMAC's approximation ability. A comparison between the CMAC performance obtained with two popular hash-coding methods is given.

    AB - Hash-coding is used in CMAC neural networks to reduce the required memory, thereby making the CMAC practical to implement. In this paper the original motivation and rationale for using hash-coding in CMAC [1] are questioned and it is shown that, contrary to the traditional believe, that hash-coding is unable to enhance CMAC's approximation ability. A comparison between the CMAC performance obtained with two popular hash-coding methods is given.

    UR - http://www.scopus.com/inward/record.url?scp=0029770205&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0029770205&partnerID=8YFLogxK

    M3 - Paper

    AN - SCOPUS:0029770205

    SP - 1698

    EP - 1703

    ER -

    Wang ZQ, Schiano JL, Ginsberg M. Hash-coding in CMAC neural networks. 1996. Paper presented at Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA, .