Toyota AI Seminar: The Soar Cognitive Architecture

In this talk, I will give an overview of the Soar cognitive architecture, starting with its origins as a rule-based system. I will describe how all of the different long-term memories (procedural, semantic, episodic), processing units (the decision procedure, mental imagery) and learning mechanisms (chunking, reinforcement learning, episodic learning) work together to support complex cognitive behavior.
John E. Laird is the John L. Tishman Professor of Engineering at the University of Michigan, where he has been since 1986. He received his Ph.D. in Computer Science from Carnegie Mellon University in 1983 working with Allen Newell. From 1984 to 1986, he was a member of research staff at Xerox Palo Alto Research Center. He is one of the original developers of the Soar architecture and leads its continued evolution, including the recent development and integration of reinforcement learning, episodic memory, semantic memory, visual and spatial mental imagery, and appraisal-based emotion. He was a founder of Soar Technology, Inc. and he is a Fellow of AAAI, ACM, and the Cognitive Science Society.