Multiple Ph.D. Positions on Deep Federated Learning in Medical Imaging

Thursday 3rd June 2021

Organization: Helmholtz AI, Helmholtz Center Munich

Location: Munich, Germany

Title: Multiple Ph.D. Positions on Deep Federated Learning in Medical Imaging

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

Email Address: shadi.albarqouni@helmholtz-muenchen.de

Description:

The Albarqouni lab develops innovative deep Federated Learning algorithms that can distill and share the knowledge among AI agents in a robust and privacy-preserved fashion. Research topics include, but are not limited to, i) handling distributed DL models with data heterogeneity including non i.i.d, and domain shifts, ii) developing explainability and quality control tools for distributed models, and iii) robustness to data and models poisoning attacks. In this context, we are looking for a PhD Candidate who has a strong background in machine/deep learning to push our understanding of the influence of data heterogeneity including non-iid and domain shift on Semi-/Fully-supervised Federated Learning algorithms, and the robustness and explainability of Federated Learning models

Closing Date: 20th June 2021