• English
  • Deutsch
  • Log In
    Password Login
    Research Outputs
    Fundings & Projects
    Researchers
    Institutes
    Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Artikel
  4. Yes we care! - Certification for machine learning methods through the care label framework
 
  • Details
  • Full
Options
September 21, 2022
Journal Article
Title

Yes we care! - Certification for machine learning methods through the care label framework

Abstract
Machine learning applications have become ubiquitous. Their applications range from embedded control in production machines over process optimization in diverse areas (e.g., traffic, finance, sciences) to direct user interactions like advertising and recommendations. This has led to an increased effort of making machine learning trustworthy. Explainable and fair AI have already matured. They address the knowledgeable user and the application engineer. However, there are users that want to deploy a learned model in a similar way as their washing machine. These stakeholders do not want to spend time in understanding the model, but want to rely on guaranteed properties. What are the relevant properties? How can they be expressed to the stake-holder without presupposing machine learning knowledge? How can they be guaranteed for a certain implementation of a machine learning model? These questions move far beyond the current state of the art and we want to address them here. We propose a unified framework that certifies learning methods via care labels. They are easy to understand and draw inspiration from well-known certificates like textile labels or property cards of electronic devices. Our framework considers both, the machine learning theory and a given implementation. We test the implementation's compliance with theoretical properties and bounds.
Author(s)
Morik, Katharina J.
Technische Universität Dortmund
Kotthaus, Helena
Technische Universität Dortmund
Fischer, Raphael
Technische Universität Dortmund
Mücke, Sascha
Technische Universität Dortmund
Jakobs, Matthias
Technische Universität Dortmund
Piatkowski, Nico  
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS  
Pauly, Andreas
Technische Universität Dortmund
Heppe, Lukas
Technische Universität Dortmund
Heinrich, Danny
Technische Universität Dortmund
Journal
Frontiers in artificial intelligence  
Project(s)
Lamarr-Institute for Machine Learning and Artificial Intelligence
Providing Information by Resource-Constrained Analysis
Funder
Bundesministerium für Bildung und Forschung -BMBF-  
Deutsche Forschungsgemeinschaft -DFG-, Bonn  
Open Access
File(s)
Download (1.97 MB)
Rights
CC BY 4.0: Creative Commons Attribution
DOI
10.3389/frai.2022.975029
10.24406/publica-616
Additional full text version
Landing Page
Language
English
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS  
Keyword(s)
  • care labels

  • certification

  • probabilistic graphical models

  • testing machine learning

  • trustworthy AI

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Contact
© 2024