A Note on the Complexity of Reliability in Neural Networks

Piotr Berman, Ian Parberry, Georg Schnitger

    Research output: Contribution to journalArticle

    Abstract

    It is shown that, in a standard discrete neural network model with small fan-in, tolerance to random malicious faults can be achieved with a log-linear increase in the number of neurons and a constant factor increase in parallel time, provided fan-in can increase arbitrarily. A similar result is obtained for a nonstandard but closely related model with no restriction on fan-in.

    Original languageEnglish (US)
    Pages (from-to)998-1002
    Number of pages5
    JournalIEEE Transactions on Neural Networks
    Volume3
    Issue number6
    DOIs
    StatePublished - Jan 1 1992

    Fingerprint

    Neural networks
    Neurons

    All Science Journal Classification (ASJC) codes

    • Software
    • Computer Science Applications
    • Computer Networks and Communications
    • Artificial Intelligence

    Cite this

    Berman, Piotr ; Parberry, Ian ; Schnitger, Georg. / A Note on the Complexity of Reliability in Neural Networks. In: IEEE Transactions on Neural Networks. 1992 ; Vol. 3, No. 6. pp. 998-1002.
    @article{f5f4105112a840b2824d34b5510d9fbb,
    title = "A Note on the Complexity of Reliability in Neural Networks",
    abstract = "It is shown that, in a standard discrete neural network model with small fan-in, tolerance to random malicious faults can be achieved with a log-linear increase in the number of neurons and a constant factor increase in parallel time, provided fan-in can increase arbitrarily. A similar result is obtained for a nonstandard but closely related model with no restriction on fan-in.",
    author = "Piotr Berman and Ian Parberry and Georg Schnitger",
    year = "1992",
    month = "1",
    day = "1",
    doi = "10.1109/72.165601",
    language = "English (US)",
    volume = "3",
    pages = "998--1002",
    journal = "IEEE Transactions on Neural Networks and Learning Systems",
    issn = "2162-237X",
    publisher = "IEEE Computational Intelligence Society",
    number = "6",

    }

    A Note on the Complexity of Reliability in Neural Networks. / Berman, Piotr; Parberry, Ian; Schnitger, Georg.

    In: IEEE Transactions on Neural Networks, Vol. 3, No. 6, 01.01.1992, p. 998-1002.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - A Note on the Complexity of Reliability in Neural Networks

    AU - Berman, Piotr

    AU - Parberry, Ian

    AU - Schnitger, Georg

    PY - 1992/1/1

    Y1 - 1992/1/1

    N2 - It is shown that, in a standard discrete neural network model with small fan-in, tolerance to random malicious faults can be achieved with a log-linear increase in the number of neurons and a constant factor increase in parallel time, provided fan-in can increase arbitrarily. A similar result is obtained for a nonstandard but closely related model with no restriction on fan-in.

    AB - It is shown that, in a standard discrete neural network model with small fan-in, tolerance to random malicious faults can be achieved with a log-linear increase in the number of neurons and a constant factor increase in parallel time, provided fan-in can increase arbitrarily. A similar result is obtained for a nonstandard but closely related model with no restriction on fan-in.

    UR - http://www.scopus.com/inward/record.url?scp=0026954631&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0026954631&partnerID=8YFLogxK

    U2 - 10.1109/72.165601

    DO - 10.1109/72.165601

    M3 - Article

    C2 - 18276496

    AN - SCOPUS:0026954631

    VL - 3

    SP - 998

    EP - 1002

    JO - IEEE Transactions on Neural Networks and Learning Systems

    JF - IEEE Transactions on Neural Networks and Learning Systems

    SN - 2162-237X

    IS - 6

    ER -