My research focuses on:

• Developing Interpretable Machine Learning methods that provide human-understandable explanations of their behavior.
• Designing Generative Methods, based on Diffusion Models and VAEs, that incorporate structural constraints, such as an internal hierarchy, into the generative process.
• Improving Object Detection in Computer Vision by aligning instance-wise feature selection in images with human-like object perception to better reflect how we process visual information.

GPA: 5.98 / 6 (Class Rank 1)

During my master’s, I was intrigued by the capabilities of ML methods, which led me to go beyond the standard curriculum, earning over 30 additional credits and publishing two papers. Selected completed courses include Deep Learning, Medical Image Analysis, Natural Language Processing, Probabilistic Artificial Intelligence, and Statistical Learning Theory. My master’s thesis focused on detecting and removing biases in ML models.

GPA: 5.84 / 6 (Class Rank 2)

With a major in Banking & Finance and a minor in Statistics, my bachelor’s has laid the foundation for my interest in quantitatively assessing and understanding the behavior of complex phenomena. My bachelor’s thesis focused on predicting stock returns with high-dimensional generalized additive models.