Close Approximations of Sigmoid Functions by Sum of Steps for VLSI Implementation of Neural Networks

Valeriu Beiu, Jan A Peperstraete, Joos Vandewalle, Rudy Lawereins

    Research output: Contribution to journalArticlepeer-review

    Abstract

    This paper is devoted to show that there are simple and accurate ways to compute a sigmoid nonlinearity and its derivative in digital hardware by sum of steps, and that threshold gate implementation of such algorithms are area-efficient when compared to other known methods.
    Original languageEnglish
    Pages (from-to)5-34
    JournalScientific Annals of Computer Science "Alexandru Ioan Cuza" University of Iaşi
    Volume40
    Publication statusPublished - Jun 1 1994

    Fingerprint

    Dive into the research topics of 'Close Approximations of Sigmoid Functions by Sum of Steps for VLSI Implementation of Neural Networks'. Together they form a unique fingerprint.

    Cite this