Building Trustworthy Machine Learning Models for Astronomy
2021-10-26, 20:30–20:45, Grand Ballroom

Astronomy is entering an era of data-driven science, due in part to modern machine learning techniques enabling powerful new ways to analyze data. This is a shift in our scientific approach, and requires us to ask an important question: Can we trust the black box? In this talk, I will overview methods for benchmarking and assessing our algorithms. This is an essential step not just for creating more robust data analysis techniques, but also for building confidence within the astronomy community to trust machine learning methods and results.


Understanding and improving machine learning