Session: Using Open Source Tools for Machine Learning

Machine learning can feel like a magic black box, especially given the wealth of proprietary solutions and vendors that exist. This beginner-friendly talk opens the box, revealing the math that underlies these services and the open source tools you can leverage in your own work. It introduces machine learning through the lens of three use cases:

  • Teaching a computer sign language (supervised learning)
  • Predicting energy usage (time-series data)
  • Using machine learning to find your next job (content-based filtering)

Each use case demonstrates techniques applicable in real-world machine learning problems. Attendees will walk away knowing what the different kinds of machine learning are, how to use open source technologies to apply them, and how to approach problems commonly encountered when practicing machine learning in the real world.

Session Speakers:

Samuel Taylor

Samuel Taylor is a data scientist with a background in software engineering and a bias for action. He likes cooking, solving problems with data, and kindness. Outside of work, he helps high school [Read More]