News Archives

RSS Feed

[Colloquium] Socially Guided Machine Learning

February 15, 2007

Watch Colloquium: 

AVI file (416 MB)
Quicktime (149 MB)


  • Date: Thursday, February 15, 2007 
  • Time: 11 am — 12:15 pm 
  • Place: ECE 118

Andrea Thomaz 
MIT

Abstract: This talk introduces a paradigm, Socially Guided Machine Learning, that takes a human-machine interaction perspective on Machine Learning. This approach asks, How can systems be designed to take better advantage of learning from a human partner and the ways that everyday people approach the task of teaching? In this talk I describe two novel social learning systems, on robotic and computer game platforms. Results from these systems show that designing agents to better fit human expectations of a social learning partner both improves the interaction for the human and significantly improves the way machines learn.

Sophie is a virtual robot that learns from human players in a video game via interactive Reinforcement Learning. A series of experiments with this platform uncovered and explored three principles of Social Machine Learning: guidance, transparency, and asymmetry. For example, everyday people were able to use an attention direction signal to significantly improve learning on many dimensions: a 50% decrease in actions needed to learn a task, and a 40% decrease in task failures during training.

On the Leonardo social robot, I describe my work enabling Leo to participate in social learning interactions with a human partner. Examples include learning new tasks in a tutelage paradigm, learning via guided exploration, and learning object appraisals through social referencing. An experiment with human subjects shows that Leo’s social mechanisms significantly reduced teaching time by aiding in error detection and correction.

Bio: Andrea Thomaz is a Post-Doctoral Associate in the Media Laboratory at the Massachusetts Institute of Technology, where she also received her Ph.D. in 2006. Previously, Andrea obtained a B.S. in Electrical and Computer Engineering from the University of Texas at Austin in 1999. Her research interests span Machine Learning, Robotics, Human-Robot Interaction, and Cognitive Science, with the goal of developing machines that learn new tasks and goals from ordinary people in everyday human environments.