Monday, February 11, 2019 - 4:00pm to 4:50pm
Weniger Hall 151

Speaker Information

Rich Caruana
Principal Researcher
Microsoft

Abstract

In machine learning often a tradeoff must be made between accuracy and intelligibility: the most accurate models (deep nets, boosted trees and random forests) usually are not very intelligible, and the most intelligible models (logistic regression, small trees and decision lists) usually are less accurate. This tradeoff limits the accuracy of models that can be safely deployed in mission-critical applications such as healthcare where being able to understand, validate, edit, and ultimately trust a learned model is important. We have developed a learning method based on generalized additive models (GA2Ms) that is as accurate as full complexity models, but more intelligible than linear models. In this talk I'll present a case study where intelligibility is critical to uncover surprising patterns in the data that would have made deploying a black-box model risky. I'll also show how we're using these models to detect bias in domains where fairness and transparency are paramount, and how these models can be used to understand what is learned by black-box models such as deep nets.

Speaker Bio

Rich Caruana is a Principal Researcher at Microsoft. His research focus is on intelligible/transparent modeling, machine learning for medical decision making, deep learning, and computational ecology. Before joining Microsoft, Rich was on the faculty in Computer Science at Cornell, at UCLA's Medical School, and at CMU's Center for Learning and Discovery. Rich's Ph.D. is from CMU, where he worked with Tom Mitchell and Herb Simon. His thesis on Multi-Task Learning helped create interest in a subfield of machine learning called Transfer Learning. Tom Dietterich was on Rich's thesis committee way back then.