On Kolmogorov's Superposition and Boolean Functions

Valeriu Beiu

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    4 Citations (Scopus)

    Abstract

    The paper overviews results dealing with the approximation capabilities of neural networks, as well as bounds on the size of threshold gate circuits. Based on an explicit numerical (i.e., constructive) algorithm for Kolmogorov's superpositions we show that for obtaining minimum size neural networks for implementing any Boolean function, the activation function of the neurons is the identity function. Since classical AND-OR implementations, as well as threshold gate implementations which require exponential size (in the worst case), it follows that size-optimal solutions for implementing arbitrary Boolean functions require analog circuitry. Conclusions and several comments on the required precision are presented.
    Original languageEnglish
    Title of host publicationIEEE Vth Brazilian Symposium on Neural Networks
    DOIs
    Publication statusPublished - Dec 9 1998
    EventSBRN'98 - Belo Horizonte, Brazil
    Duration: Dec 9 1998 → …

    Conference

    ConferenceSBRN'98
    Period12/9/98 → …

    Fingerprint

    Dive into the research topics of 'On Kolmogorov's Superposition and Boolean Functions'. Together they form a unique fingerprint.

    Cite this