A New Direction in AI Toward a Computational Theory of Perceptions
Humans have a remarkable capability to perform a wide variety of physical and mental tasks without any measurements and any computations. Familiar examples are parking a car, driving in city traffic, playing golf, cooking a meal, and summarizing a story. In performing such tasks, humans use perceptions of time, direction, speed, shape, possibility, likelihood, truth, and other attributes of physical and mental objects. Reflecting the bounded ability of the human brain to resolve detail, perceptions are intrinsically imprecise. In more concrete terms, perceptions are f-granular, meaning that (1) the boundaries of perceived classes are unsharp and (2) the values of attributes are granulated, with a granule being a clump of values (points, objects) drawn together by indistinguishability, similarity, proximity, and function. For example, the granules of age might be labeled very young, young, middle aged, old, very old, and so on.
F-granularity of perceptions puts them well beyond the reach of traditional methods of analysis based on predicate logic or probability theory. The computational theory of perceptions (CTP), which is outlined in this article, adds to the armamentarium of AI a capability to compute and reason with perception-based information. The point of departure in CTP is the assumption that perceptions are described by propositions drawn from a natural language; for example, it is unlikely that there will be a significant increase in the price of oil in the near future.
In CTP, a proposition, p, is viewed as an answer to a question, and the meaning of p is represented as a generalized constraint. To compute with perceptions, their descriptors are translated into what is called the generalized constraint language (GCL). Then, goal-directed constraint propagation is utilized to answer a given query. A concept that plays a key role in CTP is that of precisiated natural language (PNL).
The computational theory of perceptions suggests a new direction in AI—a direction that might enhance the ability of AI to deal with real-world problems in which decision-relevant information is a mixture of measurements and perceptions. What is not widely recognized is that many important problems in AI fall into this category.
KeywordsMembership Function Computational Theory Possibility Distribution Information Granulation Fuzzy Graph
Unable to display preview. Download preview PDF.
- Barsalou, L. W. 1999. Perceptual Symbol Systems. Behavioral and Brain Sciences 22: 577–660Google Scholar
- Davis, E. 1990 Representations of Commonsense Knowledge. San Francisco, Calif.: Morgan KaufmannGoogle Scholar
- de Kleer, J., and Bobrow, D. G. 1984. Qualitative Reasoning with Higher-Order Derivatives. In Proceedings of the Fourth National Conference on Artificial Intelligence. Menlo Park, Calif.: American Association for Artificial IntelligenceGoogle Scholar
- Dubois, D., and Prade, H. 1996. Approximate andCommonsense Reasoning: From Theory to Practice. In Proceedings of the Foundations of Intelligent Systems, Ninth International Symposium,19–33. Berlin: Springer-VerlagGoogle Scholar
- Dubois, D.; Fargier, H.; and Prade, H. 1994. Propagation and Satisfaction of Flexible Constraints. In Fuzzy Sets, Neural Networks, and Soft Computing, eds. R. R. Yager and L. A. Zadeh, 166–187. New York: Von Nostrand Reinhold.Google Scholar
- Geng, J. Z. 1995. Fuzzy CMAC Neural Networks. Journal of Intelligent and Fuzzy Systems 3 (1): 87–102.Google Scholar
- Kuipers, B. J. 1984. Qualitative Reasoning. Cambridge, Mass.: MIT Press.Google Scholar
- Lano, K. 1991. A Constraint-Based Fuzzy Inference System. In Proceedings of EPIA 91, Fifth Portuguese Conference on Artificial Intelligence, eds. P. Barahona, L. M. Pereira, and A. Porto, 45–59. Berlin: Springer-Verlag.Google Scholar
- Lenat, D. B. 1995. cyc: A Large-Scale Investment in Knowledge Infrastructure Communications of the ACM 38(11): 32–38Google Scholar
- McCarthy, J. 1990. Formalizing Common Sense, eds. V. Lifschitz and J. McCarthy. Norwood, N.J.: Ablex.Google Scholar
- McCarthy, J., and Hayes, P. J. 1969. Some Philosophical Problems from the Standpoint of Artificial Intelligence. In Machine Intelligence 4, eds. B. Meltzer and D. Michie, 463–502. Edinburgh: Edinburgh University Press.Google Scholar
- Mani, I., and Maybury, M. T., eds. 1999. Advances in Automatic Text Summarization. Cambridge, Mass.: MIT Press.Google Scholar
- Mavrovouniotis, M. L., and Stephanopoulos, G. 1987. Reasoning with Orders of Magnitude and Approximate Relations. In Proceedings of the Sixth National Conference on Artificial Intelligence, 626–630. Menlo Park, Calif.: American Association for Artificial Intelligence.Google Scholar
- Sandewall, E. 1989. Combining Logic and Differential Equations for Describing Real-World Systems. In Proceedings of the First International Conference on Principles of Knowledge Representation and Reasoning, 412–420. San Francisco, Calif.: Morgan KaufmannGoogle Scholar
- Shafer, G. 1976. A Mathematical Theory of Evidence. Princeton, N.J.: Princeton University PressGoogle Scholar
- Struss, P. 1990. Problems of Interval-Based Qualitative Reasoning. In Qualitative Reasoning about Physical Systems, eds. D. Weld and J. de Kleer, 288–305. San Francisco, Calif.: Morgan KaufmannGoogle Scholar
- Vallee, R. 1995. Cognition et Systeme (Cognition and Systems). Paris: l’Interdisciplinaire Systeme(s)Google Scholar
- Zadeh, L. A. 1986. Outline of a Computational Approach to Meaning and Knowledge Representation Based on the Concept of a Generalized Assignment Statement. In Proceedings of the International Seminar on Artificial Intelligence and Man-Machine Systems, eds. M. Thoma and A. Wyner, 198–211. Heidelberg: Springer-VerlagGoogle Scholar