BT/MT: »Data-Efficient Deep Learning Models in production«

At the Fraunhofer IPT in Aachen, we work with more than 530 employees every day to make the production of the future more digital, more flexible and more sustainable. In the department "production quality", we deal with the digitalization of production systems in order to increase quality, resilience and sustainability in production. 

 

The use of deep learning in computer vision systems enables quality and efficiency gains in various applications in production (e. g., visual quality control). In this context, a typical challenge is the lack of representative training data, such as data of quality-critical anomalies. Augmentation strategies for the enrichment of datasets are usually designed manually and rely on simple image manipulations (e. g., geometry or color transformations). Within the scope of your thesis, you will investigate how optimization methods (e. g., Bayesian optimization) can be used to design efficient augmentation strategies for deep learning models in production use cases. The main potential lies in the integration of synthetic data from generative models and the use of domain knowledge.

 

What you will do

• Literature research on the topics of deep learning, generative image augmentation and global optimization
• Identification of requirements for the design of efficient augmentation strategies in production use cases
• Development and implementation of a method for optimizing augmentation strategies using synthetic data and/or domain knowledge
• Experimental validation based on production use cases in the field of computer vision (e. g., visual quality control)
• Preparation and documentation of results

 

What you bring to the table

• You are studying mechanical engineering, industrial engineering, computer science or a comparable subject
• You have first experience in Python
• You have basic knowledge of the theory and methods in machine- /deep learning
• A self-responsible and structured way of working
• Good language skills in German and/or English

 

What you can expect

• Scientific work on a current and practice-relevant topic
• Opportunity to expand and deepen your knowledge in the field of deep learning models
• Professional supervision and support for your thesis
• Participation in innovative research and industry projects with industry partners
• A state-of-the-art machine park equipped with edge cloud systems and 5G infrastructure

 

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!

 

 

Maximilian Motz M.Sc.
Research assistant production quality
Phone: +49 241 8904-449

Fraunhofer Institute for Production Technology IPT 

www.ipt.fraunhofer.de 

 

Requisition Number: 69836                Application Deadline: