Interpretability of ML models is a critical aspect when designing a system to support clinical decision-making.
Camila Roa
Camila Roa uses self-supervised learning to build representation spaces for retinal image datasets, and then visualises them in 2D using neighbor embedding algorithms. She is a PhD student and part of the IMPRS-IS graduate school. Her research interests include interpretability and robustness in medical applications of machine learning.
Interpretability of ML models is a critical aspect when designing a system to support clinical decision-making.
Present Positions And Title
PhD Student
Research Group
Email Address
Career
| Period | Institution | Role |
|---|---|---|
| Since 2025 | University of Tübingen | PhD student |
| 2023 - 2024 | Oak Ridge National Laboratory, Center for AI Security Research | Graduate Research Assistant |
| 2023 | University of Southern California, Information Sciences Institute | Summer Intern |
| 2022 - 2023 | University of Tennessee, Knoxville | Graduate Research Assitant |
Academic Education
| Year | Degree | Institution | Field of Study |
|---|---|---|---|
| 2024 | MSc | University of Tennessee, Knoxville | Computer Science |
| 2022 | BSc | Pontificia Universidad Javeriana | Electronics Engineering |