Oregon State University

Calendar

Calendars

Event Details

PhD Oral Preliminary Examination – Todd Kulesza


Thursday, January 12, 2012 10:00 AM - 12:00 PM

An Explanation-Centric Approach for Personalizing Intelligent Agents
Intelligent agents have moved beyond mundane tasks like filtering junk e-mail. Search engines now exploit pattern recognition to detect image content (e.g., clipart, photography, and faces); Facebook and image editors take this a step further, making educated guesses as to who is in a particular photo. Netflix and Amazon use collaborative filtering to recommend items of interest to their customers, while Pandora and Last.fm use similar techniques to create radio stations crafted to an individual’s idiosyncratic tastes. Simple rule-based systems have evolved into agents employing complex algorithms. These intelligent agents are computer programs whose behavior only becomes fully specified after learning from an end user’s training data. Thus, end users of intelligent agents are in the unique position of needing to determine whether an agent that has learned new behavior from its user is still working as expected. Further, if the agent makes mistakes, the end user is in a position to correct (or more formally, debug) these errors.

A sound understanding of an agent’s reasoning seems a logical prerequisite for both assessing the agent’s reliability and providing useful corrections to this reasoning. My thesis work aims to understand how people reason about intelligent agents, how people communicate with intelligent agents, and how intelligent agents can improve their reasoning using these communications. I hypothesize that explaining an agent’s reasoning to end users will enable them to form better judgments of the agent’s reliability, and help users to provide feedback that can substantially improve the agent’s future predictions.

 

Major Advisor: Margaret Burnett
Committee: Weng-Keen Wong
Committee: Alex Groce
Committee: Carlos Jensen
GCR: Maggie Niess


Kelley Engineering Center (campus map)
3057
Shannon Thompson
1 541 737 7234
shannon.thompson at oregonstate.edu
Sch Elect Engr/Comp Sci
This event appears on the following calendars: