Abstract
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.
Similar content being viewed by others
References
McCarthy J: 'Programs with commonsense', in Mechanisation of Thought Processes', Proceedings of the Symposium of National Physics Laboratory, pp 77—84, London, HMSO (1959).
Singh P: 'The public acquisition of commonsense knowledge', in Proceedings of AAAI Spring Symposium: Acquiring (and Using) Linguistic (and World) Knowledge for Information Access, Palo Alto, CA, AAAI (2002).
Lenat D: 'CYC: A large-scale investment in knowledge infrastructure', Communications of the ACM, 38, No 11, pp 33—38 (1995).
Singh P, Barry B and Liu H: 'Teaching machines about everyday life', BT Technol J, 22, No 4, pp 227—250 (October 2004).
Liu H and Singh P: 'ConceptNet — a practical commonsense reasoning tool-kit', BT Technol J, 22, No 4, pp 211—226 (October 2004).
Lieberman H, Faaborg A, Espinosa J and Stocky T: 'Commonsense on the go', BT Technol J, 22, No 4, pp 241—252 (October 2004).
Carbonell J: 'Derivational analogy: A theory of reconstructive problem solving and expertise acquisition', in Michalski R, Carbonell J and Mitchell T (Eds): 'Machine learning: an artificial intelligence approach', Morgan Kaufman Publishers, San Mateo, CA (1986).
Kuipers B: 'Qualitative simulation', Artificial Intelligence, 29, pp 289—338 (1986).
Minsky M: 'K-lines, a theory of memory', Cognitive Science, 4, pp 117—133 (1980).
Davis R: 'Diagnostic reasoning based on structure and behaviour', Artificial Intelligence, 24, pp 347—410 (1984).
Winston P H: 'Learning structural descriptions from examples', PhD thesis, Department of Electrical Engineering, MIT (1970).
Sussman G J: 'A computational model of skill acquisition', PhD thesis, Department of Mathematics, MIT (1973).
Pearl J: 'Probabilistic reasoning in intelligent systems', San Mateo, CA, Morgan Kaufmann (1988).
Amarel A: 'On representations of problems of reasoning about actions', in Michie D (Ed): 'Machine intelligence', 3, No 3, pp 131—171, Elsevier (1968).
Minsky M: 'The Emotion Machine', (forthcoming).
Minsky M: 'The society of mind', New York, Simon and Schuster (1986).
Polya G: 'How to solve it: a new aspect of mathematical method', Princeton, NJ, Princeton University Press (1957).
Singh P: 'A preliminary collection of reflective critics for layered agent architectures', Proceedings of the Safe Agents Workshop (AAMAS 2003), Melbourne, Australia (2003).
Lakoff G and Johnson M: 'Metaphors We Live By', University of Chicago Press (1980).
Singh P and Minsky M: 'An architecture for combining ways to think', Proceedings of the International Conference on Knowledge Intensive Multi-Agent Systems, Cambridge, MA (2003).
Singh P and Minsky M: 'An architecture for cognitive diversity', in Davis D N (Ed): 'Visions of Mind', IDEA Group Inc (2004).
McCarthy J, Minsky M, Sloman A, Gong L, Lau T, Morgenstern L, Mueller E, Riecken D, Singh M and Singh P: 'An architecture of diversity for commonsense reasoning', IBM Systems Journal, 41, No 3, pp 530—539 (2002).
Minsky M, Singh P and Sloman A: 'The St Thomas commonsense symposium: designing architectures for human-level intelligence', AI Magazine, 25, No 2, pp 113—124 (2004).
About this article
Cite this article
Singh, P., Minsky, M. & Eslick, I. Computing Commonsense. BT Technology Journal 22, 201–210 (2004). https://doi.org/10.1023/B:BTTJ.0000047599.89995.3c
Issue Date:
DOI: https://doi.org/10.1023/B:BTTJ.0000047599.89995.3c