Proposals

---

Current

Finding hidden features responsible for machine learning failures Data representativity, similarity, and diversity Fairness and bias in multi-task learning with demographics Meta-prediction of machine learning performance

---

Previous

Parallels of medical imaging and natural language processing Skin lesion classification with crowdsourced similarity ratings Estimating the impact of Kaggle classification challenges Responsible implementation AI-based radiological protocol recommendation in Denmark Debiasing medical image datasets to improve machine learning robustness and fairness Exploring connections of spectral learning priority and learning task

Projects

---

Current

---

Previous