DETECT: Towards edge-optimized deep learning for explainable quality control

Project description:

The current evolution of the manufacturing domain towards the so-called Industry 4.0 demands for more flexible solutions. Deep Neural Networks (DNNs) provide this by automatically learning high level features. However, its wide-spread application   in industry is mainly hampered by two factors: high hardware demands and lacking explainability of classification decisions.  Neural networks tend to rely heavily on features which are unintuitive for human perception. This makes it difficult to justify decisions without profound knowledge of the technology. In consequence, DNNs are currently unsuited for human-machine-interaction, which is a major design principle of Industry 4.0. 

  • Starting date: 01/01/2020
  • Duration: 48 months
  • Funding source: FNR IF   
  • Researchers: Joe Lorentz, Prof. Djamila Aouada  
  • Partners: DataThings