"Interactive Machine Learning: Leveraging Human Intelligence"
Dan R. Olsen, Jr.,
Professor of Computer Science at Brigham Young University

12:00 Noon on Thursday, November 10, 2005
TSRB 118 - Auditorium

Advances in processor speed and in machine learning algorithms have brought machine learning within the interactive time scale. It is now possible on many problems for a user to annotate data, train a classifier and receive feedback on the classification in 4-5 seconds. This very tight feedback loop on machine learning opens many possibilities for user interfaces that interactively manage far more information than the user can visualize. This not only changes the way we might interact with information but also changes the way we pose our machine learning problems. Having a user in a tight loop changes the distribution of training data as well as imposes constraints on training algorithms. This talk will explore these issues as well as present preliminary data on how humans and machine learning can interact.

Dan R. Olsen Jr. is a Professor of Computer Science at Brigham Young University. He was formerly the director of CMU's HCI Institute and founding editor of ACM's Transactions on Computer Human Interaction (TOCHI). For the last 25 years he has been working on software architectures and techniques to support the construction of user interfaces. His most recent work is in human-robot interaction and in architectures that integrate machine learning into the user interface.