Computing Commonsense

How can we build systems with 'commonsense', the thinking skills that every ordinary person takes for granted? In this paper, we describe a multi-agent architecture for enabling commonsense reasoning which is in development at the Media Lab. The system reasons about the kinds of fundamental entities that show up in nearly all situations — such as people, objects, events, goals, plans and mistakes. The architecture supports multiple layers of reflective reasoning, mechanisms for coherent reasoning across multiple representations, and large-scale control structures called 'ways to think'. We first describe the main features of our architecture and then discuss its application and evaluation to an artificial life scenario.

[1]  Hugo Liu,et al.  ConceptNet — A Practical Commonsense Reasoning Tool-Kit , 2004 .

[2]  G. Lakoff,et al.  Metaphors We Live by , 1982 .

[3]  Henry Lieberman,et al.  Commonsense on the Go , 2004 .

[4]  Hugo Liu,et al.  Teaching Machines about Everyday Life , 2004 .

[5]  Benjamin Kuipers,et al.  Qualitative Simulation , 1986, Artificial Intelligence.

[6]  Push Singh,et al.  The Public Acquisition of Commonsense Knowledge , 2002 .

[7]  P. Campbell.  How to Solve It: A New Aspect of Mathematical Method , 2005 .

[8]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[9]  Patrick Henry Winston,et al.  Learning structural descriptions from examples , 1970 .

[10]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems , 1988 .

[11]  Push Singh,et al.  An Architecture for Cognitive Diversity , 2005 .

[12]  G. Reeke.  Marvin Minsky, The Society of Mind , 1991, Artif. Intell..

[13]  Marvin Minsky,et al.  An architecture for combining ways to think , 2003, IEMC '03 Proceedings. Managing Technologically Driven Organizations: The Human Side of Innovation and Change (IEEE Cat. No.03CH37502).

[14]  Marvin Minsky,et al.  K-Lines: A theory of Memory , 1980, Cogn. Sci..

[15]  Douglas B. Lenat,et al.  CYC: a large-scale investment in knowledge infrastructure , 1995, CACM.

[16]  Jaime G. Carbonell,et al.  Derivational analogy: a theory of reconstructive problem solving and expertise acquisition , 1993 .

[17]  Randall Davis,et al.  Diagnostic Reasoning Based on Structure and Behavior , 1984, Artif. Intell..

[18]  H. Lieberman,et al.  Common Sense on the Go : Giving Mobile Applications an Understanding of Everyday Life , 2004 .

[19]  Benjamin J. Kaipers,et al.  Qualitative Simulation , 1989, Artif. Intell..

[20]  Gerald J. Sussman,et al.  A Computational Model of Skill Acquisition , 1973 .

[21]  Aaron Sloman,et al.  An architecture of diversity for commonsense reasoning , 2002, IBM Syst. J..

[22]  Saul Amarel,et al.  On representations of problems of reasoning about actions , 1968 .

[23]  Aaron Sloman,et al.  The St. Thomas Common Sense Symposium: Designing Architectures for Human-Level Intelligence , 2004, AI Mag..