An Introduction to Machine Learning Interpretability


By registering for this or any DATAVERSITY® event, as applicable by local privacy laws, you agree to receive marketing e-mail notifications from DATAVERSITY, sponsors, and partners from this event. Use of this contact data is governed by each individual entity’s Privacy Policy. Just click the “unsubscribe” or "Manage Your Email Subscriptions" link in any e-mail to unsubscribe.

Sponsored by:

About the Paper

H2OAIWPCover.pngUnderstanding and trusting models and their results is a hallmark of good science. However, today, the trade-off between the accuracy and interpretability of predictive models has been broken. But, tools now exist to build accurate and sophisticated modeling systems based on heterogeneous data and machine learning algorithms and to enable human understanding and trust in these complex systems.

Download this new O'Reilly eBook, An Introduction to Machine Learning Interpretability, to learn to make the most of recent and disruptive breakthroughs in debugging, explainability, fairness, and interpretability techniques for machine learning.


Data Education for Business and IT Professionals