PhD in Deep Federated Learning with Medical Imaging (Data Heterogeneity)

03.06.2021, Wissenschaftliches Personal

Your responsibilities:

• Build and create clinical use-cases for benchmarking existing state-of-the-art (SOTA) Federated Learning algorithms. This includes running a few pre-processing pipelines.

• Develop SOTA FL algorithms that tackle data heterogeneity; namely non-iid and domain shift, e.g. multi-modal data acquired by different scanners and imaging protocols.

• Publish and present scientific results at international conferences and high-impact journals.

• Close collaboration with team members and colleagues.

Essential qualifications:

• M.Sc. in Computer Science, Machine Learning, or equivalent with interest in Medical Imaging and Deep Learning.

• Strong knowledge in Machine/Deep Learning with experience in discriminative models, domain adaptation, and variational inference.

• Excellent analytical, technical, and problem solving skills

• Excellent programming skills in Python and PyTorch including fundamental software engineering principles and machine learning design patterns.

• Be highly motivated and a team player with excellent communication and presentation skills, including experience in communicating across discipline boundaries.

• Fluent command of the English language

Desirable qualifications:

• Track record of publications at top-tier conferences and high-impact journals in the field

• Hands-on experience with Federated Learning frameworks.

• Hands-on experience with MONAI framework.

• Working in a Linux environment, with experience of shell scripting, cluster, or cloud computing.

• Fluency in spoken and written German.

Kontakt: shadi.albarqouni@helmholtz-muenchen.de

Mehr Information

https://albarqouni.github.io/team/