Hello KC Data Scientists!

Please join us this evening, October 29th, to discuss interpretable machine learning and the techniques that go behind making a white-box model! Following is a brief agenda for the evening:

6:00 - 6:30 PM: Doors open for networking and pizza

6:30 - 7:15 PM: Talk on Machine Learning Interpretability

7:15 - 7:30 PM: Q&A

7:30 - 8:00 PM: Networking

Description:

Machine learning systems are used today to make life-altering decisions about employment, bail, parole, and lending. Moreover, the scope of decisions delegated to machine learning systems seems likely only to expand in the future. Unfortunately, serious discrimination, privacy, and even accuracy concerns can be raised about these systems. Many researchers and practitioners are tackling disparate impact, inaccuracy, privacy violations, and security vulnerabilities with a number of brilliant, but often siloed, approaches. This presentation illustrates how to combine innovations from several sub-disciplines of machine learning research to train explainable, fair, trustable, and accurate predictive modeling systems. Together these techniques can create a new and truly human-centered type of machine learning suitable for use in business- and life-critical decision support.

Speakers:

Bahador Khaleghi

Bahador’s unique technical background, which he has gained over the last thirteen years, is quite diverse entailing a wide range of disciplines including machine learning, statistical information fusion, and signal processing. He obtained his PhD from CPAMI at the University of Waterloo. Over the last seven years, he has actively contributed to industrial R&D projects in various domains including Telematics, mobile health, predictive maintenance, and customer analytics. In his last role, Bahador acted as the technical lead of the explainability team at Element AI and was focused on developing and applying methodologies that enhance transparency, trustability, and accessibility of AI solutions.

Keith Weisz

Keith is a Machine Learning Evangelist and a Data Strategist at H2O.ai, based in Kansas City. His expertise is helping organizations align their business goals with their data strategy. Taking into account people, process and technology, he helps enterprises leverage their data assets to gain market share, improve profits and/or reduce risk.