There are 3 machine learning topics I am actively thinking about a lot these days:
Topic #1: Evaluation
I am interested in evaluation because it is at the core of every functioning real-world machine learning system.
Kaggle introduced me to it—and since then, I have learned a lot about the importance of baseline models, i.i.d., and cross-validation.
Topic #2: Reproducibility
I first got interested in reproducibility 13 years ago.
And my hope is that over the next year as an SSI fellow, as I continue to learn and share more, I'll be able to help move reproducibility in machine learning applications in science along.
Topic #3: Operations
I also have an interest in learning more about ML ops.
It's one of those fun rabbit holes I find growing deeper and deeper with every topic I read up on.
It would be great to connect with other people who are interested in these same topics — so if any of the above resonates, feel free to reach out!