Unified Tooling for Machine Learning Interpretability
Who is this presentation for?Data Scientists, Machine Learning Engineers, Software Engineers
In machine learning often a tradeoff must be made between accuracy and intelligibility: the most accurate models usually are not very intelligible (e.g., random forests, boosted trees, and neural nets), and the most intelligible models usually are less accurate (e.g., linear or logistic regression). Interpretability research has focused on minimizing this tradeoff, by developing more accurate interpretable models, and by developing new techniques to explain “blackbox” models.
In this talk, we will walk the audience through a framework for thinking about interpretability, and help them choose the right interpretability method for a variety of real world tasks. We will also present new tooling from Microsoft that helps with all forms of interpretability — both training accurate, interpretable models and understanding “blackbox” models. This toolkit includes the first Python implementation of a powerful new learning algorithm developed here: GA2M.
Prerequisite knowledgeExperience training and evaluating machine learning systems.
What you'll learn
Harsha is a data scientist at Microsoft. He works on interpretability and privacy for Machine Learning.
Sam is a data scientist at Microsoft. He works on interpretability for machine learning.
Rich Caruana is a Principal Researcher at Microsoft Research. Before joining Microsoft, Rich was on the faculty in the Computer Science Department at Cornell University, at UCLA’s Medical School, and at CMU’s Center for Learning and Discovery. Rich’s Ph.D. is from Carnegie Mellon University, where he worked with Tom Mitchell and Herb Simon. His thesis on Multi-Task Learning helped create interest in a new subfield of machine learning called Transfer Learning. Rich received an NSF CAREER Award in 2004 (for Meta Clustering), best paper awards in 2005 (with Alex Niculescu-Mizil), 2007 (with Daria Sorokina), and 2014 (with Todd Kulesza, Saleema Amershi, Danyel Fisher, and Denis Charles), co-chaired KDD in 2007 (with Xindong Wu), and serves as area chair for NIPS, ICML, and KDD. His current research focus is on learning for medical decision making, transparent modeling, deep learning, and computational ecology.
Leave a Comment or Question
Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?
Join the conversation here (requires login)
For conference registration information and customer service
For more information on community discounts and trade opportunities with O’Reilly conferences
For information on exhibiting or sponsoring a conference
View a complete list of Strata Data Conference contacts