A Note on the Complexity of Reliability in Neural Networks

Piotr Berman, Ian Parberry, Georg Schnitger

    Research output: Contribution to journalArticlepeer-review

    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 - Nov 1992

    All Science Journal Classification (ASJC) codes

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

    Fingerprint Dive into the research topics of 'A Note on the Complexity of Reliability in Neural Networks'. Together they form a unique fingerprint.

    Cite this