Approximate Machine Learning

Approximate Machine Learning is a machine learning methodology that belongs to the class of computational techniques designed for scalable and efficient learning from large-scale data, differentiated by its deliberate trade-off of precision for computational efficiency through controlled approximations in model training, inference, or data representation.

118

Publications

11.4K

Citations

340

Authors

157

Institutions

Publications per year

2017–2026

57

Authors

340

  1. LC
    Luís Ceze

    University of Washington, United States

    3 publications · 752 citations

    3

    h-index

  2. HE
    Hadi Esmaeilzadeh

    Georgia Institute of Technology, United States

    3 publications · 752 citations

    3

    h-index

  3. DB
    Doug Burger

    The University of Texas at Austin, United States

    3 publications · 752 citations

    3

    h-index

  4. AS
    Adrian Sampson

    University of Washington, United States

    3 publications · 752 citations

    3

    h-index

  5. PL
    Pier Luca Lanzi

    Politecnico di Milano, Italy

    3 publications · 209 citations

    3

    h-index

1–5 of 340

Venues

  1. arXiv (Cornell University)

    Repository · 11 publications · 302 citations

    10

    h-index

  2. IEEE Transactions on Neural Networks

    3 publications · 116 citations

    3

    h-index

  3. Neurocomputing

    3 publications · 119 citations

    3

    h-index

  4. 3

    h-index

  5. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 3 publications · 143 citations

    3

    h-index

1–5