Mixture Of Experts

Mixture of Experts is a type of ensemble learning model in which a gating network dynamically assigns input instances to specialized submodels, or "experts," each trained on distinct regions of the input space to improve overall predictive performance.

311

Publications

47.1K

Citations

1.1K

Authors

337

Institutions

Publications per year

2017–2026

114

Authors

1.1K

  1. RE
    Reza Ebrahimpour

    Shahid Rajaee Teacher Training University, Iran

    8 publications · 658 citations

    8

    h-index

  2. JG
    Joydeep Ghosh

    The University of Texas at Austin, United States

    7 publications · 220 citations

    7

    h-index

  3. MF
    M.C. Fairhurst

    University of Kent, United Kingdom

    6 publications · 155 citations

    6

    h-index

  4. FR
    Fuad Rahman

    University of Kent, United Kingdom

    6 publications · 155 citations

    6

    h-index

  5. MI
    Michael I. Jordan

    University of California, Berkeley, United States

    6 publications · 8.3K citations

    6

    h-index

1–5 of 1.1K

Venues

  1. arXiv (Cornell University)

    Repository · 32 publications · 15.3K citations

    18

    h-index

  2. Neural Computation

    11 publications · 13.2K citations

    11

    h-index

  3. Expert Systems with Applications

    9 publications · 567 citations

    9

    h-index

  4. Neurocomputing

    7 publications · 334 citations

    7

    h-index

  5. Neural Networks

    6 publications · 638 citations

    6

    h-index

1–5