THESIS: TRUSTWORTHY FEDERATED DEEP LEARNING IN RESOURCE-CONSTRAINED EDGE ENVIRONMENTS
Federated deep learning has become an emerging paradigm for collaborative learning in large-scale distributed systems with a massive number of networked clients, such as smartphones, connected vehicles or edge devices. Compared to other distributed learning approaches, federated learning allows the clients to train models without sharing raw data, which achieves privacy-preserving machine learning in real application scenarios. This brings great opportunities for deploying AI approaches in future intelligent traffic systems by means of V2X communication networks.
What you will do
As part of your master thesis, you will conduct focused study on how to apply federated learning methods for distributed training on resource-constraint edge environment. You will develop, implement, analyze and validate information theoretic or empirical models for federated learning. Furthermore, you will support our colleagues in research projects for cooperative intelligent traffic systems, where you can deploy your models in real world. We also encourage you to bring your own ideas about the thesis on this research topic, In this case, please include a two-page thesis proposal in your applications.
What you bring to the table
- High motivation in creative AI research and its applications in communication networks
- Very good grades in computer science, mathematics or engineering with fundamental knowledge in deep learning
- Knowledge in the field of federated learning is preferable
- Very good programming skills in Python
- Experience with machine learning frameworks, e. g., Pytorch
- Ambition for achieving results in AI research
- Ability to work independently and resourcefully
- Good presentation skills within research discussions
What you can expect
- Versatile and practical projects in cooperative intelligent traffic systems Fraunhofer is the largest organisation for application-oriented research in Europe. Our thematic fields are oriented towards people‘s needs: Health, safety, communication, mobility, energy and the environment. We are creative, we shape technology, we design products, we improve processes, we open up new paths.
- Professional supervision
- Motivated teams in an open-minded working atmosphere
- Research infrastructure with a large number of edge computers, sensors and a powerful computer cluster
The Fraunhofer Institute for Transportation and Infrastructure Systems IVI in Dresden employs more than 100 scientists in four departments. The institute cooperates closely with the TU Dresden, the TU Bergakademie Freiberg and the Ingolstadt University of Applied Sciences.
The Fraunhofer Application Center »Connected Mobility and Infrastructure« in Ingolstadt as a new structural unit of the Fraunhofer IVI was founded in 2019 and uses the existing synergies from the competences of the THI and the Fraunhofer IVI, especially in its start-up phase. The plan is to develop further fields of technology in the coming years in the areas of autonomous systems, digitalisation in transport and vehicle and road safety.
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!
If you are interested, please apply quoting the reference number IVI-Hiwi-00695 and include the following documents: If you would like to contribute your own ideas about your thesis in this research topic, please also include a two-page thesis proposal in your application. Rui Song
- Cover letter
- CV
- Bachelor‘s transcript
- Master‘s transcript
Your contact for application:
rui.song@ivi.fraunhofer.de
Phone +49 (0) 172 5169897
Fraunhofer Application Center »Connected Mobility and Infrastructure«
Postal address
Technische Hochschule Ingolstadt
Esplanade 10
85049 Ingolstadt
www.ivi.fraunhofer.de
Fraunhofer Institute for Transportation and Infrastructure Systems IVI
Requisition Number: IVI-Hiwi-00 695 Application Deadline:
Job Segment:
Environmental Engineering, Training, Computer Science, Engineer, Engineering, Education, Technology, Research