Entropy Minimization

Entropy Minimization is a regularization strategy in semi-supervised learning that enforces confident predictions on unlabeled data by reducing the entropy of the model's output probability distribution, thereby promoting low-density separation between classes.

890

Publications

59.9K

Citations

2.3K

Authors

833

Institutions

Publications per year

2017–2026

365

Authors

2.3K

  1. MG
    Marc Garland

    Institute of Chemical and Engineering Sciences, Singapore

    31 publications · 1.2K citations

    20

    h-index

  2. LC
    Lingen Chen

    Naval University of Engineering, China

    16 publications · 1.4K citations

    15

    h-index

  3. EW
    Effendi Widjaja

    Institute of Chemical and Engineering Sciences, Singapore

    20 publications · 960 citations

    14

    h-index

  4. TH
    Tasawar Hayat

    Quaid-i-Azam University, Pakistan

    14 publications · 1.2K citations

    13

    h-index

  5. JC
    José C. Prı́ncipe

    University of Florida, United States

    14 publications · 1K citations

    12

    h-index

1–5 of 2.3K

Venues

  1. arXiv (Cornell University)

    Repository · 76 publications · 3.7K citations

    28

    h-index

  2. Pattern Recognition

    13 publications · 579 citations

    13

    h-index

  3. IEEE Transactions on Signal Processing

    13 publications · 1.7K citations

    13

    h-index

  4. International Journal of Heat and Mass Transfer

    12 publications · 421 citations

    12

    h-index

  5. 11

    h-index

1–5