Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
  A theory of independent mechanisms for extrapolation in generative models

Besserve, M., Sun, R., Janzing, D., & Schölkopf, B. (2021). A theory of independent mechanisms for extrapolation in generative models. In Proceedings of the AAAI Conference on Artificial Intelligence (pp. 6741-6749).

Item is

Basisdaten

einblenden: ausblenden:
Genre: Konferenzbeitrag

Externe Referenzen

einblenden:
ausblenden:
Beschreibung:
-
OA-Status:

Urheber

einblenden:
ausblenden:
 Urheber:
Besserve, M1, 2, Autor           
Sun, R3, Autor
Janzing, D3, Autor           
Schölkopf, B3, Autor           
Affiliations:
1Department Physiology of Cognitive Processes, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497798              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              
3Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society, ou_1497647              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: Deep generative models reproduce complex empirical data but cannot extrapolate to novel environments. An intuitive idea to promote extrapolation capabilities is to enforce the architecture to have the modular structure of a causal graphical model, where one can intervene on each module independently of the others in the graph. We develop a framework to formalize this intuition, using the principle of Independent Causal Mechanisms, and show how over-parameterization of generative neural networks can hinder extrapolation capabilities. Our experiments on the generation of human faces shows successive layers of a generator architecture implement independent mechanisms to some extent, allowing meaningful extrapolations. Finally, we illustrate that independence of mechanisms may be enforced during training to improve extrapolation.

Details

einblenden:
ausblenden:
Sprache(n):
 Datum: 2021-05
 Publikationsstatus: Online veröffentlicht
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: -
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: 35th AAAI Conference on Artificial Intelligence: A Virtual Conference
Veranstaltungsort: -
Start-/Enddatum: 2021-02-02 - 2021-02-09

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: Proceedings of the AAAI Conference on Artificial Intelligence
Genre der Quelle: Konferenzband
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: -
Seiten: - Band / Heft: 35 (8) Artikelnummer: - Start- / Endseite: 6741 - 6749 Identifikator: -