A cognitive architecture is a hypothesis about the fixed structures comprising a mind, whether natural or artificial. It is analogous to a computer architecture in providing a general level of programmability, but concerns creating an inherently cognitive – or intelligent – system rather than simply a computational system. A complete cognitive architecture must support in real time the integration of memory and reasoning, decision making and planning, adaptation and learning, and interaction with both physical and social worlds. Even when less than complete, such systems can provide value as the minds of virtual humans, intelligent agents and robots; and as nascent unified theories of human cognition. Sigma is an attempt to build such an architecture from the ground up based on graphical models, a highly efficient, theoretically elegant, and broadly applicable technology for computing with complex multivariate expressions. The goal is to leverage this breadth in blending symbolic high-level cognition with quantitative low-level processing; this theoretical elegance in constructing the diversity of requisite intelligent functionality from interactions among a small very general set of primitives; and this efficiency to build systems capable of practical application. In this talk I will provide background on Sigma, how it works, and how far we have come towards a complete cognitive architecture.

Paul S. Rosenbloom is Professor of Computer Science at the University of Southern California and Director for Cognitive Architecture Research at USC’s Institute for Creative Technologies. He was a key member of USC’s Information Sciences Institute for two decades, leading new directions activities over the second decade, and finishing his time there as Deputy Director. Earlier he was on the faculty at Carnegie Mellon University (where he had also received his MS and PhD in computer science) and Stanford University (where he had also received his BS in mathematical sciences, with distinction). His research concentrates on cognitive architectures – models of the fixed structure underlying minds, whether natural or artificial – and on understanding the nature, structure and stature of computing as a scientific domain. He is: a Fellow of both the Association for the Advancement of Artificial Intelligence (AAAI) and the Cognitive Science Society; a co-developer of Soar, one of the longest standing and most well developed cognitive architectures, during much of its early evolution; the primary developer of Sigma, which blends insights from earlier architectures such as Soar with ideas from graphical models; and the author of On Computing: The Fourth Great Scientific Domain (MIT Press, 2012).