Advertisement for subjects such as: Automatisierungstechnik, Elektrotechnik, Informatik, Kybernetik, Luft- und Raumfahrttechnik, Maschinenbau, Mathematik, Physik, Regelungstechnik, Softwaredesign, Softwareengineering, technische Informatik, Technologiemanagement or similar.

Explaining the predictions of ML models remains an important yet challenging task for the successful application of ML-based solutions, especially in safety-critical domains. A frequently used explanation method is SHAP (SHapley Additive exPlanations), which measures the contribution of each input feature to the prediction. However, interpreting these explanations can be challenging.

What you will do

In this thesis, you will implement and evaluate the feasibility of a novel explanation method inspired by SHAP. This method will generate a set of explanations represented by a tree, potentially offering a more intuitive understanding of model predictions.

What you bring to the table

  • Experience in Python programming and the ability to write clean and well-structured code
  • Prior experience with machine learning and common frameworks such as TensorFlow, PyTorch, or scikit-learn is a plus
  • Knowledge of German is a plus

What you can expect

  • Opportunity to work at the intersection of research and industry within one of Europe's leading AI ecosystems
  • Contribute to actual industrial projects with code that is implemented in real-world applications
  • Employment as a research assistant (HiWi) for the duration of your thesis contract

We value and promote the diversity of our employees' skills and therefore welcome all applications - regardless of age, gender, nationality, ethnic and social origin, religion, ideology, disability, sexual orientation and identity. Severely disabled persons are given preference in the event of equal suitability. 

With its focus on developing key technologies that are vital for the future and enabling the commercial utilization of this work by business and industry, Fraunhofer plays a central role in the innovation process. As a pioneer and catalyst for groundbreaking developments and scientific excellence, Fraunhofer helps shape society now and in the future. 

Interested? Apply online now. We look forward to getting to know you!
 

Frau Jennifer Leppich
Recruiting
Tel. +49 711 970-1415

jennifer.leppich@ipa.fraunhofer.de

Fraunhofer Institute for Manufacturing Engineering and Automation IPA 

www.ipa.fraunhofer.de 

Requisition Number: 72930                Application Deadline:

Location

Stuttgart, DE, 70569

Job Overview
Job Posted:
8 months ago
Job Expires:
Job Type
Full Time

Share This Job: