Thrifty Machine Learning


Go to NumFOCUS academy page.

We live with an abundance of ML resources; from open source tools, to GPU workstations, to cloud-hosted autoML. What’s more, the lines between AI research and everyday ML have blurred; you can recreate a state-of-the-art model from arxiv papers at home. But can you afford to? In this talk, we explore ways to recession-proof your ML process without sacrificing on accuracy, explainability, or value.


Rebecca Bilbro

Rebecca is a machine learning engineer, Python and Go programmer, teacher, speaker, and author in Raleigh, NC. She is an active contributor to the open source community, and the creator of Yellowbrick, an open source Python library that extends scikit-learn models into Visualizers using matplotlib.

She has been a speaker at PyCon, delivering a 2016 talk about visual diagnostics for machine learning that mapped out the foundations of the Yellowbrick project, and in 2017 on building a custom corpus for natural language processing. She has also given talks at O’Reilly Strata NYC, PyData Carolinas, PyData London, PyData San Luis, and EuroSciPy.

In addition to her work on Yellowbrick, Rebecca is co-author of the O’Reilly book, Applied Text Analysis with Python and emeritus board member for Data Community DC - a not-for-profit organization that organizes free monthly events and lectures for the local data community in Washington, DC.