Meta-initialization

Meta-Initialization is a meta-learning strategy that establishes an optimal starting point in parameter space for rapid adaptation to new tasks by encoding prior knowledge across related learning episodes.

49

Publications

3.7K

Citations

210

Authors

67

Institutions

Publications per year

2017–2026

46

Authors

210

  1. CK
    Constantine Kreatsoulas

    United States Military Academy, United States

    3 publications · 44 citations

    3

    h-index

  2. CQ
    Cuong Q. Nguyen

    GlaxoSmithKline (Netherlands), Netherlands

    3 publications · 44 citations

    3

    h-index

  3. KB
    Kim Branson

    Stanford University, United States

    3 publications · 44 citations

    3

    h-index

  4. HY
    Han-Jia Ye

    Nanjing University, China

    2 publications · 62 citations

    2

    h-index

  5. TW
    Terrance Wang

    University of California, Berkeley, United States

    2 publications · 232 citations

    2

    h-index

1–5 of 210

Venues

  1. arXiv (Cornell University)

    Repository · 15 publications · 1.8K citations

    13

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 2 publications · 75 citations

    2

    h-index

  3. ChemRxiv

    Repository · 2 publications · 24 citations

    2

    h-index

  4. 2

    h-index

  5. Neural Computing and Applications

    1 publications · 78 citations

    1

    h-index

1–5