Craig Stanfill
Abstract
The intensive use of memory to recall specific episodes from the past—rather than rules—should be the foundation of machine reasoning.
- 1 Alterman, R. Issues in adaptive planning. Rep. UCB/CSD 87/304, Computer Science Division, Univ. of California at Berkeley. July 1986. Google Scholar
Digital Library
- 2 Charniak, E. The Bayesian basis of common sense medical diagnosis. In Proceedings of fhe 3rd Nafional Conference on Arfificial Intelligence (AAAI-83) (Washington, D.C. Aug. 22-X). American Association for Artificial Intelligence. Menlo Park. Calif. 1983, pp. 70-73.Google Scholar
- 3 Cheeseman. P. A method for computing Bayesian probability values for expert systems. In Proceediugs of fhe 8th International \oinr Conference ou Artificial Intelligence (Karlsruhe, West Germany, Aug. 8-12). 1983. pp. 198-202.Google Scholar
- 4 DeJong. G. and Mooney, R. Explanation-based learning: An alternative view. Mach. Learn. 1, 2 (Apr. 1986), 145-176. Google ScholarDigital Library
- 5 Dreyfus, H., and Dreyfus, S. Why computers may never think like people. Technol. Rev. 89, 1 (Jan. 1986), 42-61.Google Scholar
- 6 Fahlman. S.E. NE'TL: A Sysrem for Representing and Using Real-World Knoroledge. MIT Press, Cambridge, Mass., 1979.Google Scholar
- 7 Feldman, J.A. Introduction to the special issue on connectionism. Cognitive Sci. 9, 1 (Jan.-Mar. 1985), l-169.Google Scholar
- 8 Feldman. J.A., and Ballard. D.H. Connectionist models and their properties. Cognifiue Sci. 6, 3 (July-Sept. 1982). 205-254.Google Scholar
- 9 Gelerntner. H. Realization of a aeometrv theorem proving machine. In Compufers and Thought. E.A. Feigenbaum and J.-Feldman, Eds. McGraw-Hill. New York. 1963. Google ScholarDigital Library
- 10 Hewitt, C. Description and theoretical analysis of PLANNER. Doctoral dissertation, Dept. of Mathematics, MIT, Cambridge, Mass., 1972.Google Scholar
- 11 Hillis. D. The Connection Machine. MIT Press, Cambridge, Mass., 1985. Google ScholarDigital Library
- 12 Hillis, W.D. and Steel. G.L. Jr. Data parallel algorithms. Commun. ACM 29, 12 (Dec. 1986). Google ScholarDigital Library
- 13 Hinton. G., and Anderson, J., Eds. Parallel Models of Associative Memory. Lawrence Erlbaum Associates, Hillsdale. N.J., 1981. Google ScholarDigital Library
- 14 Holland, J. Adaptation in Natural and Artificial Sysrems. University of Michigan Press, Ann Arbor, Mich., 1975. Google ScholarDigital Library
- 15 Hopfield. J.J. Neural networks and physical systems with emergent collective computational abilities. Proc. Nafl. Acad. Sci. 79 (1982). 2554-2558.Google Scholar
- 16 Kanerva, P. Self-propagating search: A unified theory of memory. Rep. CSLI-84-7, Canter for the Study of Language and Information, Stanford University. Calif., Mar. 1984.Google Scholar
- 17 Kolodner, J. Retrieval and Organizarional Strafegies in Conceptual Memorw: A Comoufer Model. Lawrence Erlbaum Associates, Hillsdale, N:J. 1984. 'Google Scholar
- 18 Kowalski, R.A. Predicate logic as programming language. In Proceedings of the IFIPS Congress (Amsterdam). International Federation of Information Processing Societies, 1974, pp. 570-574.Google Scholar
- 19 Lebowitz, M. Integrated learning: Controlling explanation. Cognifive Sri. IO, 2 (Apr.-Jo& 1986). 219-240.Google Scholar
- 20 Lcbowitz. M. Not the path to perdition: The utility of similaritybased learning. In Proceedings of the 5fh National Conference on Artificial Intelligence (AAAI-86) (Philadelphia, Pa. Aug. 11-15). American Association for Artificial Intelligence, Menlo Park. Calif., 1986, pp. 533-537.Google Scholar
- 21 Lee. W. Decision Theory and Human Behavior. Wiley, New York, 1971.Google Scholar
- 22 McClelland, J.L. and Rumelhart, D.E., Eds. Parallel Distributed Processing: E.rplorafions in the Microsfrucrure of Cognition. MIT Press, Cambi+dge. Mass., 1986. Google ScholarDigital Library
- 23 Merriam-Webster's Pockef Dictionary. Merriam-Webster. Springfield. Mass., 1974.Google Scholar
- 24 Michalski, R., CarbonelI, J,, and Mitchell, T., Eds. Machine Learning. Tioga, Palo Alto, Calif. 1983.Google Scholar
- 25 Michalski. R. Carbonell, 1. and Mitchell, T. Eds. Machine Learning. Vol. 2. Tioga. Palo Alto, Calif. 1986.Google Scholar
- 26 Miller. G.A. Gelenter. E. and Pribram, K. Plans and the Struclure of Behavior. Holt. Rinehart and Winston, New York, 1960.Google Scholar
- 27 Minsky, M. The Sociefy of Minds. Simon and Schuster. New York: To be published. Google ScholarDigital Library
- 28 Mitchell. T., Utgoff, P. and Banerji, R. Learning by experimentation: Acquiring and refining problem-solving heuristics. In Machine Learning. R. Michalski et. al., Eds. Tioga, Palo Alto, Calif. 1983.Google Scholar
- 29 Mooney, R. A domain independent explanation-based generalizer. In Proceedings of rhe 5th National Conference on Artificial Inrelligence (AAAI-86) (Philadelphia, Pa. Aug. 11-15). American Association for Artificial Intelligence, Menlo Park, Calif., 1986, pp. 551-555.Google Scholar
- 30 Newell, A. The knowledge level. Al Mag. 2, 2 (Summer 1981), l-20.Google Scholar
- 31 Newell, A. and Simon, H. Human Problem Solving. Prentice-Hall. Engelwood Cliffs, N.J., 1972. Google ScholarDigital Library
- 32 Newell, A., and Simon, H.A. GPS, a program that simulates human thought. In Compufers and Thoughr, E.A. Feigenbaum and J. Feldman, Eds. McGraw-Hill. New York, 1963, pp. 279-293. Google ScholarDigital Library
- 33 Newell, A., Ernst. G., and Shaw, J. Elements of a theory of human problem solving. Psycho/. Rev. 65, (1958). 151-166.Google Scholar
- 34 Quinlan. J.R. Discovering rules from large collections of examples: A case study. In Expert Systems in the Micro Elecfronic Age, D. Michia. Ed. Edinburgh University Press, Edinburgh, 1979.Google Scholar
- 35 Robinson, J.A. A machine-oriented logic based on the resolution principle. J. ACM 12, 1 (Jan. 1965). 23-41. Google ScholarDigital Library
- 36 Rosenblatt, F. Principles of Neurodynamics: Percepfions and Theory of Brain Mechanisms. Spartan, Washington, D.C., 1961.Google Scholar
- 37 Rumelhart, D.E. Hinton, G.E., and Williams, R.J. Learning internal representations by error propagation. In Parallel Distributed Processing: Explorafions in the Microstructure of Cognition, J.L. McClelland and D.E. Rumelhart, Eds. MIT Press, Cambridge, Mass., 1986. Google ScholarDigital Library
- 38 Samuel, A. Some studies in machine learning using the game of checkers. IBM I. Res. Dew. 3, 3 (1959). 210-299.Google ScholarDigital Library
- 39 Samuel, A. Some studies in machine learning using the game of checkers II. IBM 1. Res. DPU. 11, 6 (1967), 601-617.Google Scholar
- 40 Schank, RX., Dynamic Memory: A Theory of Reminding and Learning in Computers and People. Cambridge University Press, New York. 1982. Google ScholarDigital Library
- 41 Sejnowski. T.J., and Rosenberg. CR. NETtalk: A parallel network that learns to read aloud. Electrical Engineering and Computer Science Dept., Johns Hopkins Univ. Tech. Rep. JHU/EECS-86/01, 1986.Google Scholar
- 42 Shortliffe. E. Cornpurer Based Medical Consulkzfions: MYCIN. Elsevier North-Holland, New York, 1976.Google Scholar
- 43 Stanfill, C., and Kahle, B. Parallel free-text search on the Connection Machine system. Co~nmun. ACM 29,12 (Dec. 1986), 1229-1239. Google ScholarDigital Library
- 44 Sussman, G. Winograd, T., and Charniak. E. MICRO-PLANNER reference manual. Al Memo 203a, MIT AI Laboratory, MIT, Cambridge, Mass., Dec. 1971. Google ScholarDigital Library
- 45 Waltz, D.L., Genesereth, M., Hart, P., Hendrix, G., Joshi, A., McDermott. J. Mitchell, T., Nilsson. N., Wilensky, R., and Woods, W. Artificial intelligence: An assessment of the state-of-the-art and recommendation for future directions. AZ Mag. 4, 3 (Fall 19831, 55-67.Google Scholar
- 46 Winston, P. Learning structural descriptions from examples. In The Psychology of Computer Vision, P. Winston, Ed. McGraw-Hill, New York. 1975.Google Scholar
- 47 Woods, W.A. Transition network grammars for natural-language analysis. Commun. ACM 13, 10 (Oct. 1970). 591-606. Google ScholarDigital Library
Index Terms
- Toward memory-based reasoning
Recommendations
Abductive case-based reasoning: Research Articles
This article introduces abductive case-based reasoning (CBR) and attempts to show that abductive CBR and deductive CBR can be integrated in clinical process and problem solving. Then it provides a unified formalization for integration of abduction, ...
A unified 2d representation of fuzzy reasoning, CBR, and experience based reasoning
KES'06: Proceedings of the 10th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part IFuzzy reasoning, case-based reasoning (CBR) and experience-based reasoning (EBR) or natural reasoning have been seriously studied for years. However, these studies essentially can be considered as a 1-dimensional approach, because their reasoning ...
Linguistic hesitant fuzzy multi-criteria decision-making method based on evidential reasoning
Linguistic hesitant fuzzy sets LHFSs, which can be used to represent decision-makers’ qualitative preferences as well as reflect their hesitancy and inconsistency, have attracted a great deal of attention due to their flexibility and efficiency. This ...
Reviews
Razvan Andonie
The memory-based reasoning hypothesis is based on the following assumption: There is no general way to search memory for the best match without examining every element of memory. This paper describes an experimental memory-based reasoning system for pronouncing English words. The system has been implemented on a parallel architecture, specifically the Connection Machine. The algorithm seeks to make decisions by “remembering” similar circumstances in the past. This is done by (1) counting combinations of features, (2) using these counts to produce a metric, (3) using the metric to find the dissimilarity between the current problem and every item in the memory, and (4) retrieving the best matches. Von Neumann machines do not support such a task well. The ideal machine for memory-based reasoning would have a parallel, highly interconnected, fine-grained SIMD architecture. More important than the details of implementation and the experimental results are the conclusions and prospects derived from such an approach. Emphasis is put on the differences between memory-based and rule-based reasoning. The paper excellently fulfills its basic purpose—to explore a possible reasoning framework that can play an important role in building truly intelligent systems.
Access critical reviews of Computing literature here
Become a reviewer for Computing Reviews.
Comments