Although some claim you must start with advanced math to use deep learning, the best way for any coder to get started is with code. Rachel Thomas explains how fast.ai’s Practical Deep Learning for Coders course uses Jupyter notebooks to provide an environment that encourages students to learn deep learning through experimentation. Fast.ai wanted to help students get results fast (with no math prerequisites), so it taught them in a code-centric, application-focused way. These students are now using deep learning to identify chainsaw noise in endangered rain forests, create translation resources for Pakistani languages, reduce farmer suicides in India, diagnose breast cancer, and more. Rachel shares lessons, tips, and best practices for learning deep learning effectively so that you can set out on your own learning journey in a Jupyter notebook.
Rachel Thomas was selected by Forbes as one of “20 Incredible Women in AI”, was an early engineer at Uber, and earned her math PhD at Duke. She is co-founder of fast.ai, which created the “Practical Deep Learning for Coders” course that over 200,000 students have taken, and she is also a professor at the University of San Francisco Data Institute. Rachel is a popular writer and keynote speaker on the topics of data science ethics, bias, machine learning, and technical education. Her writing has been read by nearly a million people and has made the front page of Hacker News 9×.
For exhibition and sponsorship opportunities, email jupytersponsorships@oreilly.com
For information on trade opportunities with JupyterCon, email partners@oreilly.com
View a complete list of JupyterCon contacts
©2017, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • confreg@oreilly.com