A goal of interactive machine learning (IML) is to create robots or intelligent agents that can be easily taught how to

perform tasks by individuals with no specialized training. To achieve that goal, researchers and designers must understand

how certain design decisions impact the human’s experience of teaching the agent, such as influencing the agent’s

perceived intelligence. We posit that the type of feedback a robot can learn from affects the perceived intelligence of

the robot, similar to its physical appearance. This talk will discuss different methods of natural language instruction including critique and

and action advice. We conducted multiple human-in-the-loop experiments in which people trained agents with different

teaching methods but, unknown to each participant, the same underlying machine learning algorithm. The results show that the mechanism

of teaching has an impact on human teacher’s perception of the agent including feelings of frustration, perceptions of intelligence and performance while only minimally impacting the agent’s performance.

 

Karen Feigh is an Associate Professor in the Daniel Guggenheim School of Aerospace Engineering. She holds a B.S. in Aerospace Engineering from Georgia Tech, a MPhil in Aeronautics from Cranfield University, UK, and a Ph.D. in Industrial and Systems Engineering from Georgia Tech. Karen has previously worked on fast-time air traffic simulation, conducted ethnographic studies of airline and fractional ownership operation control centers, and designed expert systems for air traffic control towers. Her doctoral work was conducted at Georgia Tech's Cognitive Engineering Center where she used cognitive engineering methods to improve support system design methods to more closely match the dynamic needs of airline operations managers to aid with recovery from irregular operations. Her awards include the Marshall scholarship and the AIAA Orville and Wilbur Wright Graduate award.