Symposium on Reasoning and Learning in Cognitive Systems

Stanford University, March 20-21, 2004


Over the past decade, the field of machine learning has made great strides in developing computational methods for acquiring knowledge from experience. Advances have focused on the problems of classification, involving mainly supervised learning from labeled training cases, and reactive control, dealing mostly with learning from delayed reward. Both areas have seen steady progress on both the theoretical and practical fronts, with many learning techniques now being used regularly in commerce and industry.

Unfortunately, this emphasis on classification and control has meant little effort has been devoted to other important facets of cognitive systems. In particular, there has been relatively little work on methods for acquiring knowledge to use in reasoning and problem solving, despite the importance of these tasks to the construction of intelligent systems. What distinguishes humans from animals is not their ability to categorize objects or control actions, but their capacity for chaining together knowlege elements to draw inferences and generate plans.

Despite the mainstream community's focus on other areas, some enlightened researchers have designed, implemented, and evaluated systems that address learning for these more complex tasks. However, they are spread across a number of communities and publish in different venues. These include fields like cognitive modeling, AI planning, and interactive knowledge capture. Because of this topic's central importance to AI and cognitive science, it seems important to bring together these distinct groups to exchange ideas and lessons.

To this end, we have organized a symposium on reasoning and learning in cognitive systems. The meeting will bring together researchers from these different areas, let them report their recent results, and discuss common concerns. This interaction should pave the way for increased work on this topic and collaborations between some of the active groups.

Time and location

The symposium will take place on Saturday, March 20, and Sunday, March 21, just before the AAAI Spring Symposia, at Stanford University's Center for the Study and Language and Information (CSLI). Talks will be held in the main conference room of Cordura Hall on the Stanford campus.

Other information

There is no registration fee for the symposium, but attendance will be by invitation only. There will be 14 invited speakers presenting at the meeting over two days. We will have space for some non-presenting attendees at the meeting. If you are interested in participating, please send email to with a brief account of your previous and current work on the symposium topic.

We have reserved rooms at the SLAC Guest House for speakers. This new facility has inexpensive lodging and a shuttle to the main campus, so we encourage others to stay there as well.



This symposium has received financial support from the National Science Foundation, and the Office of Naval Research, along with administrative support from the Institute for the Study of Learning and Expertise and the Computational Learning Laboratory at Stanford University.