Pruning Sensitivity Analysis

Pruning Sensitivity Analysis is a methodological procedure in machine learning that systematically evaluates the impact of removing specific components from a neural network to determine their relative importance to model performance.

31

Publications

1.5K

Citations

96

Authors

34

Institutions

Publications per year

2017–2026

17

Authors

96

  1. IC
    I. Cloete

    Stellenbosch University, South Africa

    3 publications · 277 citations

    3

    h-index

  2. XZ
    Xiaoqin Zeng

    Hohai University, China

    3 publications · 114 citations

    3

    h-index

  3. AP
    Andries P. Engelbrecht

    University of Pretoria, South Africa

    3 publications · 276 citations

    3

    h-index

  4. ÉF
    Éric Fock

    Laboratoire Génie Industriel, France

    2 publications · 122 citations

    2

    h-index

  5. SA
    Salem Ameen

    University of Salford, United Kingdom

    2 publications · 212 citations

    2

    h-index

1–5 of 96

Venues

  1. arXiv (Cornell University)

    Repository · 7 publications · 119 citations

    7

    h-index

  2. IEEE Internet of Things Journal

    2 publications · 75 citations

    2

    h-index

  3. Neurocomputing

    2 publications · 153 citations

    2

    h-index

  4. Neural Computing and Applications

    2 publications · 27 citations

    2

    h-index

  5. IEEE Transactions on Neural Networks

    2 publications · 303 citations

    2

    h-index

1–5