A high-speed analog neural processor

P. Masa, Peter Masa, Klaas Hoen, Klaas Hoen, Hans Wallinga

    Research output: Contribution to journalArticleAcademicpeer-review

    12 Citations (Scopus)
    945 Downloads (Pure)

    Abstract

    Targeted at high-energy physics research applications, our special-purpose analog neural processor can classify up to 70 dimensional vectors within 50 nanoseconds. The decision-making process of the implemented feedforward neural network enables this type of computation to tolerate weight discretization, synapse nonlinearity, noise, and other non-ideal effects. Although our prototype does not take advantage of advanced CMOS technology, and was fabricated using a 2.5-μm CMOS process, it performs 6 billion multiplications per second, with only 2 W dissipation, and has as high as 1.5 Gbyte/s equivalent bandwidth.
    Original languageEnglish
    Pages (from-to)40-50
    JournalIEEE micro
    Volume14
    Issue number3
    DOIs
    Publication statusPublished - 1994

    Keywords

    • METIS-112055
    • IR-15181

    Fingerprint Dive into the research topics of 'A high-speed analog neural processor'. Together they form a unique fingerprint.

    Cite this