I’m a PhD Candidate at the Chair for Artificial Intelligence in Medicine (TUM) and member of the Konrad Zuse School for Excellence in Reliable AI. Before starting my PhD, I graduated from Imperial College London with an MSc. in Advanced Computing and a BSc. from the University of Sussex.

My research is broadly focused around theoretical and practical aspects of trust and reliability in machine learning (ML) for medicine. I’m particularily interested in:

  • understanding why and how neural networks memorise their training data
  • improving utility & reliability of differentially private ML
  • bias and fairness issues related to the deployment of ML models
  • ML for scientific discovery and precision medicine

Interests

  • Differential Privacy
  • Fair & Trustworthy ML
  • Memorisation in Neural Networks

Education

  • MSc. Advanced Computing, 2022

    Imperial College London

  • BSc. Computer Science & AI, 2020

    University of Sussex