Mehil B. Shah

I am a PhD Student in the Faculty of Computer Science at Dalhousie University. I am currently being advised by Prof. Masud Rahman, and Prof. Foutse Khomh. My primary research interests are at the intersection of Software Engineering and Deep Learning, with a focus on secure, reliable, and explainable deep learning systems. My current research focuses on understanding the behaviour of bugs in deep learning systems and trying to improve the reproducibility of deep learning bugs.

My research interests center on enhancing the reproducibility of bugs in deep learning systems. I investigate methods to systematically identify, document, and reproduce software bugs that emerge in these systems. As deep learning becomes increasingly deployed in critical applications, bugs can have significant consequences yet are notoriously difficult to reproduce due to their stochastic nature, hardware dependencies, and complex environmental interactions. By developing better tools and methodologies for bug reproduction, I aim to improve the reliability of deep learning systems and advance the field’s debugging practices.