Next SERC Talks “Can Graphical Models Provide a Sufficient Basis for General Intelligence?” on WED, APRIL 5, 2017

SERC Talks

The next SERC Talk of the ongoing Cyber-Physical Learning Systems Series will be held on Wednesday, April 5, 2017 at 1 PM EST. Dr. Paul Rosenbloom from the Institute for Creative Technologies at University of Southern California will be discussing the following topic: “Can Graphical Models Provide a Sufficient Basis for General Intelligence?Dr. Rosenbloom will also be talking about his work on Sigma, which is an attempt to build such an architecture from the ground up. We hope you can join us in this open discussion.Research in Action June 2015

TOPIC: “Can Graphical Models Provide a Sufficient Basis for General Intelligence?”

SPEAKER: Dr. Paul Rosenbloom, USC Institute for Creative Technologies

Questions and comments are welcome during the Talk itself, utilizing the Q&A and chat tools, respectively. For those unable to connect to the WebEx tool, please feel free to email your questions or comments ahead of time to Ms. Mimi Marcus for incorporation into the discussion.

NOTE: All Talks will be broadcast on WebEx. Review these system requirements to assure your connection to the webinar will be uninterrupted.  If you have any trouble with this platform,
please contact us.



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).


To view the full event page, go here. More information on future SERC Talks can be found here. The SERC Talk sessions will be recorded and available for viewing on the SERC YouTube Channel and the SERC Talks page following the event.

Please mark your calendars and plan to join us!