Dr. Thomas G. Dietterich is Distinguished Professor (Emeritus) of Computer Science at Oregon State University and Chief Scientist of BigML, a machine learning startup company. As one of the founders of the field of machine learning, Dietterich has published more than 200 scientific papers. Dietterich's research seeks methods for enabling AI systems to robustly deal with "unknown unknowns". He also leads projects in applying AI to biological conservation, management of invasive species, and policies for controlling wildfire. He is applying machine learning methods to automatically detect errors in big data applications including weather data collected by the Trans-Africa Hydrometeorological Observatory (TAHMO), which is a sustainable development project throughout sub-Saharan Africa. Dietterich is a Fellow of the Association for the Advancement of Science, the Association for Computing Machinery, and the Association for the Advancement of Artificial Intelligence. He serves as Past President of the Association for the Advancement of Artificial Intelligence, founding President of the International Machine Learning Society, and former Executive Editor of the journal Machine Learning.
Title:Robust Artificial Intelligence: Why and HowArtificial intelligence (AI) technologies are being employed in a wide range of applications. Some of these involve high risks to human lives or to the economy. As a field, we need to develop algorithms and methodologies for ensuring the safe behavior of AI systems. This talk will describe some methods for guaranteeing safe behavior. I will consider both the "known unknowns" setting, where we have an explicit model of our uncertainty, and the "unknown unknowns" setting, where our model is incomplete or misspecified. Examples will be drawn from recent work on risk-sensitive planning for ecosystem management and anomaly detection for machine learning in open worlds.