Symposium on Advances in Cognitive Architectures

Stanford University, March 22-23, 2003


A cognitive architecture specifies the underlying infrastructure for an intelligent system. Briefly, an architecture includes those aspects of a cognitive agent that are constant over time and across different application domains. The specification of a cognitive architecture consists of its representational assumptions, the characteristics of its memories, and the processes that operate on those memories.

Research on cognitive architectures is important because it supports a central goal of artificial intelligence and cognitive science: the creation and understanding of synthetic agents that support the same capabilities as humans. Unlike expert systems, cognitive architectures aim for breadth of coverage across a diverse set of tasks and domains. More important, they offer accounts of intelligent behavior at the systems level, rather than at the level of component methods designed for specialized tasks.

Despite continuing progress on cognitive architectures, a number of different themes have started to emerge within the research community. One thrust has emphasized learning, especially the acquisition and refinement of skills or policies that produce action. Another group has focused instead on how affect and emotion influence an agent's behavior. Yet another sub-community has dealt with how an architecture can allocate scarce resources like perceptual attention.

Clearly, each of these different facets of an architecture is relevant to the others. To explore these relationships, we are organizing a symposium on advances in cognitive architectures, with a special emphasis on learning and motivation. The meeting will bring together researchers in these different areas, letting them report their recent results and discuss common concerns. This interaction should pave the way for the development of more unified architectures that model the relations between learning and affect.

A secondary theme will explore issues of scalability in cognitive architectures, which arise as we apply them to complex real-world problems, and modularity in such architectures, as we attempt to combine the best ideas from different theoretical frameworks. The second afternoon of the meeting will address these methodological challenges and alternative responses to them.

Time and location

The symposium will take place on Saturday, March 22, and Sunday, March 23, 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 a few 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.



This symposium has received financial support from the Defense Advanced Projects Agency, the National Science Foundation, and the Office of Naval Research, along with administrative support from:

  • Institute for the Study of Learning and Expertise

  • Computational Learning Laboratory at Stanford University

  • Artificial Intelligence Laboratory at the University of Michigan