Pruning Level

Pruning Level is a methodological parameter within model compression techniques that specifies the extent of structural reduction applied to a neural network, distinguishing it by quantifying the proportion of parameters or neurons removed relative to the original architecture.

15

Publications

396

Citations

42

Authors

20

Institutions

Publications per year

2017–2026

4

Authors

42

  1. DC
    David C. Ferree

    The Ohio State University, United States

    2 publications · 59 citations

    2

    h-index

  2. YT
    Yuta Teranishi

    Nara Institute of Science and Technology, Japan

    1 publications · 18 citations

    1

    h-index

  3. LP
    L. Peter Christensen

    University of California, Davis, United States

    1 publications · 13 citations

    1

    h-index

  4. DM
    D. McE. Alexander

    Commonwealth Scientific and Industrial Research Organisation, Australia

    1 publications · 24 citations

    1

    h-index

  5. NC
    Neil C. Turner

    The University of Western Australia, Australia

    1 publications · 90 citations

    1

    h-index

1–5 of 42

Venues

  1. American Journal of Enology and Viticulture

    AJEV · 2 publications · 62 citations

    2

    h-index

  2. 2

    h-index

  3. Journal of Advances in Information Technology

    JAIT · 1 publications · 18 citations

    1

    h-index

  4. Agroforestry Systems

    1 publications · 34 citations

    1

    h-index

  5. arXiv (Cornell University)

    Repository · 1 publications · 17 citations

    1

    h-index

1–5