Peter Ma

About

I am a first-year graduate student with a keen interest in applying Machine Learning to a range of (astro)physical challenges, including instrument design, theory/equation discovery, and observational (anomally) detection pipelines. My current work focuses on neural network-based adaptive optics for the Rubin Observatory and the development of neural compression techniques to optimize data transfer for future space-based telescopes.

I completed my undergraduate degree in Applied Mathematics at the University of Toronto. During that time, I developed real-time deep learning algorithms for detecting Fast Radio Bursts, created graph neural networks to explore dark matter substructures in the Milky Way, and designed firmware for implementing neural networks on FPGAs for the Large Hadron Collider at CERN. I also worked on developing neural networks for high-frequency feedback control to enhance gravitational wave detection at LIGO.

I am an advocate for multidisciplinary research and I am a strong believer that the frontiers of science are hiding at the intersection of many different fields.