Our society increasingly relies on intelligent machines. Algorithms decide which e-mails reach our inboxes, whether we're approved for credit, and whom we get the opportunity to date.
An interpretable algorithm is one whose decisions you can explain. You can better rely on such a model to be safe, accurate and useful. And an accurate model that is also interpretable can offer insights that can be used to change real-world outcomes for the better.
But the most powerful approaches to machine intelligence, including random forests, gradient boosting and neural networks, can be uninterpretable black boxes.Â
In this webinar we'll learn about recent research, new tools and commercial applications of machine learning interpretability.
This webinar is for a general audience and will cover the technical content at a conceptual level.
Host — Mike Lee Williams, Research Engineer, Fast Forward Labs (@mikepqr, LinkedIn)
Guest — Sameer Singh, Assistant Professor of Computer Science at the University of California, Irvine (@sameer_)
Sameer is part of the team that created LIME, a model-agnostic tool for extracting explanations from black box machine learning models. He works on large-scale and interactive machine learning applied to information extraction and natural language processing.
Â
Guest — Patrick Hall, Senior Director for Data Science Products at H2o.ai (@jpatrickhall, LinkedIn)
Patrick Hall is a senior director for data science products at H2o.ai where he focuses mainly on model interpretability. Patrick is also currently an adjunct professor in the Department of Decision Sciences at George Washington University, where he teaches graduate classes in data mining and machine learning.