Thesis - Enhancing Machine Learning Transparency through Data Attribution
Advertisement for subjects such as: all fields of study. 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 rather novel method is data attribution, where specific test predictions are attributed to the training data. We are interested in practical applications of these methods to ensure the safety and reliability of ML in real-world scenarios.
What you will do
This thesis can take one of two directions: you can focus on the technical side and implement or improve current data attribution methods. Alternatively, you can focus on the applied side and derive best practices and recommendations for the use of data attribution methods. In this case, you could conduct interviews with practitioners.
What you bring to the table
What you can expect
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 jennifer.leppich@ipa.fraunhofer.de
Recruiting
Tel. +49 711 970-1415
Fraunhofer Institute for Manufacturing Engineering and Automation IPA
Requisition Number: 72929 Application Deadline:
Job Segment:
Research Assistant, Manufacturing Engineer, Learning, Machinist, Research, Engineering, Human Resources, Manufacturing