Representation Learning For Transfer

Representation Learning for Transfer is a machine learning methodology that acquires latent feature spaces from simulation environments to enable effective knowledge transfer to real-world domains by preserving task-relevant invariances and minimizing domain shift.

103

Publications

8K

Citations

391

Authors

188

Institutions

Publications per year

2017–2026

80

Authors

391

  1. BS
    Bernhard Schölkopf

    Max Planck Institute for Intelligent Systems, Germany

    5 publications · 115 citations

    5

    h-index

  2. SB
    Stefan Bauer

    Max Planck Institute for Intelligent Systems, Germany

    5 publications · 115 citations

    5

    h-index

  3. FL
    Francesco Locatello

    Max Planck Institute for Intelligent Systems, Germany

    4 publications · 101 citations

    4

    h-index

  4. MW
    Manuel Wüthrich

    Max Planck Institute for Intelligent Systems, Germany

    4 publications · 101 citations

    4

    h-index

  5. MW
    Muhammad Waleed Gondal

    Max Planck Institute for Biological Cybernetics, Germany

    3 publications · 85 citations

    3

    h-index

1–5 of 391

Venues

  1. arXiv (Cornell University)

    Repository · 15 publications · 518 citations

    13

    h-index

  2. Neurocomputing

    3 publications · 174 citations

    3

    h-index

  3. Knowledge-Based Systems

    3 publications · 49 citations

    2

    h-index

  4. Reliability Engineering & System Safety

    2 publications · 212 citations

    2

    h-index

  5. MPG.PuRe (Max Planck Society)

    Repository · 2 publications · 59 citations

    2

    h-index

1–5