Deep learning has already revolutionized machine-learning research, but it remains opaque to many developers. Yufeng Guo and Amy Unruh explain just how easy it is to get started with advanced machine learning by live-coding a wide and deep learning model—a deep neural network classifier—training it using TensorFlow’s tf.learn library, and evaluating it. Along the way, Yufeng and Amy cover feature selection, feature crosses, bucketing and the hashing trick, categorical versus continuous features and how to change between them, hidden units, and hyperparameter tuning. You’ll leave ready to use deep learning on your own data.
Amy Unruh is a developer programs engineer for the Google Cloud Platform, where she focuses on machine learning and data analytics as well as other Cloud Platform technologies. Amy has an academic background in CS/AI and has also worked at several startups, done industrial R&D, and published a book on App Engine.
©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. • firstname.lastname@example.org