LIVIVO - Das Suchportal für Lebenswissenschaften

switch to English language
Zurück zur letzten Suche Suchhistorie
Erweiterte Suche

Ihre letzten Suchen

  1. AU="Jung, Hee-Jun"
  2. AU="Struckmann, Stephan"
  3. AU=Coward Richard
  4. AU="Ghazizadeh, Shabnam"
  5. AU="Rebecca A Butcher"
  6. AU="Kimberlyn Roosa"
  7. AU=Chian Ri-Cheng
  8. AU="Alzalzalah, Sayed"
  9. AU=Kaufman Jonathan J
  10. AU="Kim, Jin K"
  11. AU="Zevakov, S A"
  12. AU="Sui Phang"
  13. AU="Kolomeichuk, Lilia V"
  14. AU="Sabuj Kanti Mistry"
  15. AU="Basurto-Lozada, Daniela"
  16. AU="Takashima, Shin-Ichiro"
  17. AU="Teresinha Leal"
  18. AU="Angélique B van 't Wout"
  19. AU="Roberts, Nicholas J"
  20. AU="Chauhan, Gaurav B"
  21. AU=Hanjaya-Putra Donny
  22. AU=Powell James
  23. AU="Russell, Todd"
  24. AU=Forth Scott
  25. AU="Kreutzer, Susanne" AU="Kreutzer, Susanne"
  26. AU="St John, Maie"
  27. AU=Gerhardy A
  28. AU="Qi, Huixin"
  29. AU="Dobosiewicz, May"
  30. AU="Srivastava, Rakesh"
  31. AU="Grevtsov K.I."

Suchergebnis

Treffer 1 - 2 von insgesamt 2

Suchoptionen

  1. Buch ; Online: CFASL

    Jung, Hee-Jun / Jeong, Jaehyoung / Kim, Kangil

    Composite Factor-Aligned Symmetry Learning for Disentanglement in Variational AutoEncoder

    2024  

    Abstract: Symmetries of input and latent vectors have provided valuable insights for disentanglement learning in VAEs.However, only a few works were proposed as an unsupervised method, and even these works require known factor information in training data. We ... ...

    Abstract Symmetries of input and latent vectors have provided valuable insights for disentanglement learning in VAEs.However, only a few works were proposed as an unsupervised method, and even these works require known factor information in training data. We propose a novel method, Composite Factor-Aligned Symmetry Learning (CFASL), which is integrated into VAEs for learning symmetry-based disentanglement in unsupervised learning without any knowledge of the dataset factor information.CFASL incorporates three novel features for learning symmetry-based disentanglement: 1) Injecting inductive bias to align latent vector dimensions to factor-aligned symmetries within an explicit learnable symmetry codebook 2) Learning a composite symmetry to express unknown factors change between two random samples by learning factor-aligned symmetries within the codebook 3) Inducing group equivariant encoder and decoder in training VAEs with the two conditions. In addition, we propose an extended evaluation metric for multi-factor changes in comparison to disentanglement evaluation in VAEs. In quantitative and in-depth qualitative analysis, CFASL demonstrates a significant improvement of disentanglement in single-factor change, and multi-factor change conditions compared to state-of-the-art methods.

    Comment: 21 pages, 14 figures
    Schlagwörter Computer Science - Machine Learning ; Computer Science - Artificial Intelligence
    Erscheinungsdatum 2024-01-16
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  2. Buch ; Online: Feature Structure Distillation with Centered Kernel Alignment in BERT Transferring

    Jung, Hee-Jun / Kim, Doyeon / Na, Seung-Hoon / Kim, Kangil

    2022  

    Abstract: Knowledge distillation is an approach to transfer information on representations from a teacher to a student by reducing their difference. A challenge of this approach is to reduce the flexibility of the student's representations inducing inaccurate ... ...

    Abstract Knowledge distillation is an approach to transfer information on representations from a teacher to a student by reducing their difference. A challenge of this approach is to reduce the flexibility of the student's representations inducing inaccurate learning of the teacher's knowledge. To resolve it in transferring, we investigate distillation of structures of representations specified to three types: intra-feature, local inter-feature, global inter-feature structures. To transfer them, we introduce feature structure distillation methods based on the Centered Kernel Alignment, which assigns a consistent value to similar features structures and reveals more informative relations. In particular, a memory-augmented transfer method with clustering is implemented for the global structures. The methods are empirically analyzed on the nine tasks for language understanding of the GLUE dataset with Bidirectional Encoder Representations from Transformers (BERT), which is a representative neural language model. In the results, the proposed methods effectively transfer the three types of structures and improve performance compared to state-of-the-art distillation methods. Indeed, the code for the methods is available in https://github.com/maroo-sky/FSD.

    Comment: This work has been submitted to the ELSEVIER for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible
    Schlagwörter Computer Science - Computation and Language ; Computer Science - Artificial Intelligence ; Computer Science - Machine Learning
    Thema/Rubrik (Code) 004
    Erscheinungsdatum 2022-04-01
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

Zum Seitenanfang