• English
  • Deutsch
  • Log In
    Password Login
    or
  • Research Outputs
  • Projects
  • Researchers
  • Institutes
  • Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. The Good, the Bad and the Ugly: Augmenting a black-box model with expert knowledge
 
  • Details
  • Full
Options
2019
Conference Paper
Titel

The Good, the Bad and the Ugly: Augmenting a black-box model with expert knowledge

Abstract
We address a non-unique parameter fitting problem in the context of material science. In particular, we propose to resolve ambiguities in parameter space by augmenting a black-box artificial neural network (ANN) model with two different levels of expert knowledge and benchmark them against a pure black-box model.
Author(s)
Heese, R.
Fraunhofer-Institut für Techno- und Wirtschaftsmathematik ITWM
Walczak, M.
Fraunhofer-Institut für Techno- und Wirtschaftsmathematik ITWM
Morand, L.
Fraunhofer-Institut für Werkstoffmechanik IWM
Helm, D.
Fraunhofer-Institut für Werkstoffmechanik IWM
Bortz, M.
Fraunhofer-Institut für Techno- und Wirtschaftsmathematik ITWM
Hauptwerk
Artificial Neural Networks and Machine Learning - ICANN 2019. Workshop and Special Sessions. Proceedings
Konferenz
International Conference on Artificial Neural Networks (ICANN) 2019
Thumbnail Image
DOI
10.1007/978-3-030-30493-5_38
Externer Link
Externer Link
Language
English
google-scholar
Fraunhofer-Institut für Techno- und Wirtschaftsmathematik ITWM
Fraunhofer-Institut für Werkstoffmechanik IWM
Tags
  • expert knowledge

  • mixture of experts

  • custom loss

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Send Feedback
© 2022