Cross Entropy

Cross Entropy is a measure of the difference between two probability distributions for a given random variable or set of events, defined as the expected number of bits needed to identify an event drawn from one distribution when using a coding scheme optimized for another distribution.

1.7K

Publications

154.7K

Citations

5.6K

Authors

1.4K

Institutions

Publications per year

2017–2026

1.1K

Variants

Cross-entropy

Authors

5.6K

  1. DP
    Dirk P. Kroese

    The University of Queensland, Australia

    21 publications · 4.3K citations

    18

    h-index

  2. PS
    Pengjian Shang

    Beijing Jiaotong University, China

    12 publications · 384 citations

    12

    h-index

  3. RY
    Reuven Y. Rubinstein

    Technion – Israel Institute of Technology, Israel

    9 publications · 4K citations

    9

    h-index

  4. JY
    Jun Ye

    Shaoxing University, China

    8 publications · 698 citations

    8

    h-index

  5. JC
    Jung-Chieh Chen

    National Kaohsiung Normal University, Taiwan

    8 publications · 319 citations

    8

    h-index

1–5 of 5.6K

Venues

  1. arXiv (Cornell University)

    Repository · 200 publications · 14.2K citations

    52

    h-index

  2. IEEE Access

    63 publications · 3.4K citations

    33

    h-index

  3. Entropy

    41 publications · 1.3K citations

    20

    h-index

  4. Remote Sensing

    23 publications · 894 citations

    19

    h-index

  5. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 27 publications · 2.9K citations

    19

    h-index

1–5