Rule-based Explanations

Rule-Based Explanations is a type of explainability method in machine learning that provides human-interpretable IF-THEN rules to characterize the decision logic of a model, distinguished by its symbolic and deterministic representation of feature-to-outcome relationships.

123

Publications

9.1K

Citations

322

Authors

176

Institutions

Publications per year

2017–2026

78

Authors

322

  1. FG
    Fosca Giannotti

    University of Pisa, Italy

    6 publications · 861 citations

    6

    h-index

  2. AM
    Anna Monreale

    University of Pisa, Italy

    5 publications · 798 citations

    5

    h-index

  3. SR
    Salvatore Ruggieri

    University of Pisa, Italy

    5 publications · 798 citations

    5

    h-index

  4. DP
    Dino Pedreschi

    University of Pisa, Italy

    5 publications · 798 citations

    5

    h-index

  5. FT
    Franco Turini

    University of Pisa, Italy

    5 publications · 798 citations

    5

    h-index

1–5 of 322

Venues

  1. arXiv (Cornell University)

    Repository · 10 publications · 448 citations

    9

    h-index

  2. IEEE Access

    5 publications · 120 citations

    5

    h-index

  3. IEEE Transactions on Fuzzy Systems

    TFS · 5 publications · 176 citations

    4

    h-index

  4. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 4 publications · 238 citations

    3

    h-index

  5. Journal of Experimental Psychology General

    3 publications · 690 citations

    3

    h-index

1–5