Patrick Hall
Patrick Hall is principal scientist at BNH.AI, where he advises Fortune 500 companies and cutting-edge startups on AI risk and conducts research in support of NIST’s AI risk management framework. He also serves as visiting faculty in the Department of Decision Sciences at The George Washington School of Business, teaching data ethics, business analytics, and machine learning classes.
Before cofounding BNH, Patrick led H2O.ai’s efforts in responsible AI, resulting in one of the world’s first commercial applications for explainability and bias mitigation in machine learning. He also held global customer-facing roles and R&D research roles at SAS Institute. Patrick studied computational chemistry at the University of Illinois before graduating from the Institute for Advanced Analytics at North Carolina State University.
Patrick has been invited to speak on topics relating to explainable AI at the National Academies of Science, Engineering, and Medicine, ACM SIG-KDD, and the Joint Statistical Meetings. He has contributed written pieces to outlets like McKinsey.com, O’Reilly Radar, and Thompson Reuters Regulatory Intelligence, and his technical work has been profiled in Fortune, Wired, InfoWorld, TechCrunch, and others.
Radar
Seven Legal Questions for Data Scientists
What to Do When AI Fails
Why you should care about debugging machine learning models
Understanding and fixing problems in ML models is critical for widespread adoption.
Ideas on interpreting machine learning
Mix-and-match approaches for visualizing data and interpreting machine learning models and results.
Content
Proposals for model vulnerability and security
Apply fair and private models, white-hat and forensic model debugging, and common sense to protect machine learning models from malicious actors.
Testing machine learning explanation techniques
The importance of testing your tools, using multiple tools, and seeking consistency across various interpretability techniques.
Ideas on interpreting machine learning
Mix-and-match approaches for visualizing data and interpreting machine learning models and results.
The preoccupation with test error in applied machine learning
Measure your model’s business impact, not just its accuracy.
Predictive modeling: Striking a balance between accuracy and interpretability
Tips for using machine learning models in regulated industries.