Machine Learning Interpretability with Driverless AI

Presented by

Patrick Hall, Andy Steinbach

About this talk

Join us for this webinar with Andy Steinbach, Head of AI in Financial Services at NVIDIA, as he moderates a discussion with Patrick Hall, Senior Data Scientist and Product Engineer at on Machine Learning Interpretability with Driverless AI. In addition to the discussion, Patrick will showcase several approaches beyond the error measures and assessment plots typically used to interpret deep learning and machine learning models and results. This will include: - Data visualization techniques for representing high-degree interactions and nuanced data structures. - Contemporary linear model variants that incorporate machine learning and are appropriate for use in regulated industry. - Cutting edge approaches for explaining extremely complex deep learning and machine learning models. Wherever possible, interpretability approaches are deconstructed into more basic components suitable for human storytelling: complexity, scope, understanding, and trust. Bio: Patrick Hall is a Senior Data Scientist and Product Engineer at and works with’s customers to derive substantive business value from machine learning technologies. His product work at focuses on model interpretability and deployment. Patrick also is an adjunct professor in the Department of Decision Sciences at George Washington University, where he teaches graduate classes in data mining and machine learning. Prior to joining, Patrick held global customer facing roles and R & D research roles at SAS Institute. Andy leads the global effort to develop the NVIDIA deep learning platform in the Financial Services Industry. He specializes in developing applications of revolutionary technologies in new markets. In his last role, he built a new group to employ machine learning technology for the first time in a $1B imaging technology division of the global technology company ZEISS.

Related topics:

More from this channel

Upcoming talks (0)
On-demand talks (111)
Subscribers (19202) is the maker of H2O, the world's best machine learning platform and Driverless AI, which automates machine learning. H2O is used by over 200,000 data scientists and more than 18,000 organizations globally. H2O Driverless AI does auto feature engineering and can achieve 40x speed-ups on GPUs.