Project

Quantifying neural network interpretability: a benchmarking approach

Duration
01 January 2020 → Ongoing
Funding
Regional and community funding: Special Research Fund
Promotor
Research disciplines
  • Natural sciences
    • Machine learning and decision making
Keywords
Machine learning interpretability neural network
 
Project description

Neural network based models are paramount in machine learning, but they are black boxes that are difficult to interpret. In this project, we propose a benchmarking study to compare the current existing techniques that extract knowledge from these models. In this way we hope to identify current potential and limitations and use these to develop new knowledge extraction methods.