Twenty-first International Joint Conference on Artificial Intelligence (IJCAI-09)

The Interdisciplinary Reach of Artificial Intelligence

Pasadena Conference Center

Sponsored by The International Joint Conferences on Artificial Intelligence (IJCAI) and The Association for the Advancement of Artificial Intelligence (AAAI)

IJCAI-09 Invited Speaker Program
Cristina Conati

Intelligent Tutoring Systems: New challenges and Directions

Cristina Conati (University of British Columbia)

Can we devise educational systems that provide individualized instruction tailored to the needs of the individual learners, as many good teachers do? Intelligent Tutoring Systems is the interdisciplinary field that investigates this question by integrating research in Artificial Intelligence, Cognitive Science and Education. Successful intelligent tutoring systems have been deployed to support traditional problem solving activities by tailoring the instruction to the student's domain knowledge.

In this talk, I will present a variety of projects that illustrate our efforts to extend the scope of intelligent tutors to both support novel forms of pedagogical interactions (e.g., example-based and exploration-based learning) and adapt to student's traits beyond knowledge (e.g., student's meta-cognitive abilities and affective states). I will discuss the challenges of this research, the results that we have achieved so far and future opportunities.

Cristina Conati is an Associate Professor of Computer Science at the University of British Columbia. She received her M.Sc. degree in Computer Science from the University of Milan, Italy (1988), and an M.Sc. (1996) and Ph.D. (1999) in Artificial Intelligence from the University of Pittsburgh. Dr. Conati's areas of interest include Adaptive Interfaces, Intelligent Tutoring Systems, UserModeling, and Affective Computing. She published over 50 strictly refereed articles, and received best paper awards from the international conferences on User Modeling, AI in Education, Intelligent User Interfaces, and the Journal of User Modeling and User-Adapted Interaction.

Thomas Dietterich

Machine Learning in Ecosystem Informatics and Sustainability

Thomas G. Dietterich (Oregon State University)

Ecosystem Informatics brings together mathematical and computational tools to address scientific and policy challenges in the ecosystem sciences. These challenges include novel sensors for collecting data, algorithms for automated data cleaning, learning methods for building statistical models from data and for fitting mechanistic models to data, and algorithms for designing optimal policies for biosphere management. This talk will describe recent work on the first two of these---new devices for automated arthropod population counting and linear Gaussian DBNs for automated cleaning of sensor network data. It will also give examples of open problems along the whole spectrum from sensors to policies.

Thomas G. Dietterich is Professor and Director of Intelligent Systems Research at Oregon State University. He is interested in fundamental AI research and in interdisciplinary research at the intersection of computer science, ecology, and sustainability policy. With lead-PI Carla Gomes (Cornell), he serves as co-PI of a 5-year NSF Expedition in Computational Sustainability. He is part of the leadership team for OSU's Ecosystem Informatics programs including the Ecosystem Informatics IGERT and the NSF Summer Institute in Ecoinformatics. He leads the BugID project, which is developing inexpensive rapid-throughput methods for automated arthropod population counting.

Photo Not Available

Embodied Language Games with Autonomous Robots

Luc Steels (Sony Computer Science Laboratory and Paris/University of Brussels)

European Coordinating Committee for Artificial Intelligence (ECCAI) Invited Speaker

Artificial Intelligence methods and techniques have reached a high level of sophistication so that we can tackle difficult outstanding problems in science. In this talk, I will show how the question of the origins of language can be approached this way. This question has puzzled evolutionary biologists since Darwin and is still considered to be unsolved. I will outline a theory of language evolution by linguistic selection and then report a number of concrete experiments with humanoid robots that attempt to work out and validate this theory. The experiments all center around the notion of a language game, which is a routinized situated interaction that involves some form of language. Robots use linguistic strategies to evolve a communication system to deal with a particular class of language games. I will discuss examples of this and also address the question how new strategies can arise and how the robots can autonomously decide which strategies they will collectively use to bootstrap their language.

Luc Steels has been active in AI since graduating from the MIT AI lab in the early nineteen eighties. He is a professor of Artificial Intelligence at the University of Brussels (VUB) and has founded the VUB Artificial Intelligence Laboratory which has been active in the domains of knowledge-based systems, dynamical systems approach to intelligence, behavior-based robotics, and most recently evolutionary linguistics. Ten years ago he founded the Sony Computer Science Laboratory in Paris and there he pursues his research in the foundations of intelligent systems, particularly in relation to the origins of language and meaning. Steels has edited a dozen books on various topics in AI and is the author of more than hundred research papers. He is a fellow of ECCAI and member of AAAI. At the moment he is a fellow at the Wissenschaftskolleg (Institute for Advanced Studies) in Berlin.

Hal Varian

Computer Mediated Transactions

Hal R. Varian (University of California, Berkeley and Google)

These days nearly every economic transaction involves a computer in some form or other. What does this mean for economics?  I argue that the ubiquity of computers enables new and more efficient contractual forms,  better alignment of incentives,  more sophisticated data extraction and analysis, creates an environment for controlled experimentation, and allows for personalization and customization.  I review some of the long and rich history of these phenomena and describe some of their implications for current and future practices.

Hal R. Varian is the Chief Economist at Google. He started in May 2002 as a consultant and has been involved in many aspects of the company, including auction design, econometric, finance, corporate strategy and public policy.

He also holds academic appointments at the University of California, Berkeley in three departments: business, economics, and information management. He received his S.B. degree from MIT in 1969 and his MA and Ph.D. from UC Berkeley in 1973. Professor Varian has published numerous papers in economic theory, econometrics, industrial organization, public finance, and the economics of information technology.

Gerhard Widmer (Johannes Kepler University Linz and Austrian Research Institute for Artificial Intelligence, Vienna, Austria)

We regret that the scheduled invited talk by Gerhard Widmer has recently been cancelled

Qiang Yang

From Low-level Sensors to High-level Intelligence: Activity Recognition Links the Knowledge Food Chain

Qiang Yang (Hong Kong University of Science and Technology)

Sensors provide computer systems with a window to the outside world. Activity recognition "sees" what is in the window to predict the locations, trajectories, actions, goals and plans of humans and objects. Building an activity recognition system requires a full range of interaction from statistical inference on lower level sensor data to symbolic AI at higher levels, where prediction results and acquired knowledge are passed up each level to form a knowledge food chain. In this talk, I will give an overview of activity recognition and explore its relation to other fields, including planning and knowledge acquisition, machine learning and Web search.  I will also describe its applications in assistive technologies, security monitoring and mobile commerce.

Qiang Yang's research interests are planning, machine learning and data mining. He received his B.Sc. in astrophysics at Peking University in 1982 and Ph.D. in computer science at the University of Maryland, College Park in 1989. He then joined the faculty of the University of Waterloo in Canada.  In 1995 he became an NSERC Industry Research Chair at Simon Fraser University in Canada. He is now a professor at Hong Kong University of Science and Technology. He is a Fellow of IEEE, member of AAAI and co-winner of two ACM KDDCUP championships. He is the author of over 200 research papers and two books: Intelligent Planning (Springer 1997) and Constraint-Based Design Recovery for Software Reengineering, with Steven Woods and Alexander Quilici (Springer, 1998).

Site last updated on 7/27/2009