Abstract
Memory-Based Reasoning (MBR) represents a radical new departure in AI research. Whereas work in symbolic AI is based on inference and knowledge representation MBR depends on using a large memory of examples as a reasoning base. The MBR methodology is empirical so a typical system does not contain an explicit domain model. This means that MBR systems are quick to set up so the methodology shows considerable promise for knowledge based systems development. Indeed some impressive full scale systems have been demonstrated. In this paper we argue that despite this initial success there are considerable limitations to what can be achieved with MBR. We believe that the absence of a domain model means that MBR will not succeed in complex applications. We illustrate problems in natural language processing and planning that will require access to domain theories in their solution. Our conclusion is that the memory oriented philosophy of MBR has advantages but, for truly intelligent systems, this philosophy is better realised in the CBR paradigm where it can be integrated with a strong domain theory.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
Brugman, C. & Lakoff, G. 1988. “Cognitive Topology and Lexical Networks”, in Lexical Ambiguity Resolution, edited by S. Small, G. Cottrell and M. Tanenhaus. San Mateo, CA: Morgan Kaufmann Publishers.
Cottrell, G. W. & S. Small. (1982). A Connectionist Scheme for Modelling Word-Sense Disambiguation. In Cognition and Brain Theory 6, pp 89–120.
Creecy R.H., Masand B.M., Smith S.J., Waltz D.L., (1992) “Trading MIPS and Memory for Knowledge Engineering: Automatic Classification of Census Returns on a Massively Parallel Supercomputer”, Communications of the ACM, pp48–64, Vol. 35, No. 8, August 1992.
Evett M.P., Andersen W.A., Hendler J. A., (1993) “Massively Parallel Support for Efficient Knowledge Representation”, In Proceedings of IJCAI-93.
Fass D., (1988). “An Account of Coherence, Semantic Relations, Metonymy, and Lexical Ambiguity Resolution”, Lexical Ambiguity Resolution: Perspectives from Psycholinguistics Neuropsychology and Artificial Intelligence Small, S. I., G. W. Cottrell & M. K. Tanenhaus, eds., Morgan Kaufmann, San Mateo, CA.
Fikes, R. E., Hart, P. E., Nilsson, N. J. (1972). Learning and Executing Generalised Robot Plans, Artificial Intelligence, 2, 251–288
Jackendoff, R. (1991). Parts and Boundaries, Lexical and Conceptual Semantics, B. Levin and S. Pinker, eds. Elsevier Science Publishers, Amsterdam.
Kitano H., (1993) “Challenges of Massive Parallelism”, Proceedings of the 13th. International Joint Conference on Artificial Intelligence, Chambery France, Morgan Kaufmann, pp813–834.
Kitano H., Higuchi T., (1991) “Massively Parallel Memory-Based Parsing”, Proceedings of the 12th. International Joint Conference on Artificial Intelligence, Sydney Australia, Morgan Kaufmann, pp918–924.
Kolodner J.L, (1991), “Improving Human Decision Making Through Case-Based Decision Aiding”, AI Magazine, Vol. 12, No. 2, Summer 1991, pp52–68.
Stanfill C., Waltz D., (1992) “Statistical Methods, Artificial Intelligence, and Information Retrieval”, in Text-Based Intelligent Systems, P. Jacobs ed., pp215–225, Lawrence Earlbaum Associates, Hillsdale, New Jersey.
Stanfill C., Waltz D., (1986) “Toward Memory-Based Reasoning”, Communications of the ACM, pp1213–1228, Vol. 29, No. 12, December 1986.
Smyth B., Cunningham P., (1992) “Déjà Vu: A Hierarchical Case-Based Reasoning System for Software Design”, in Proceedings of 10th. European Conference on Artificial Intelligence, Vienna, Austria, ed. Bernd Neumann, Wiley & Son, pp587–589, 1992.
Veloso M., Carbonell J.G., (1991), “Learning by analogical replay in PRODIGY: first results”, European Working Session on Learning, Y. Kodratoff, ed., pp375–389, Porto, Portugal, Springer Verlag.
Veale T., Keane M.T., (1992), “Conceptual Scaffolding: A Spatially Founded Meaning Representation for Metaphor Comprehension”, Computational Intelligence, 8, 494–519.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cunningham, P., Smyth, B., Veale, T. (1995). On the limitations of Memory Based Reasoning. In: Haton, JP., Keane, M., Manago, M. (eds) Advances in Case-Based Reasoning. EWCBR 1994. Lecture Notes in Computer Science, vol 984. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60364-6_28
Download citation
DOI: https://doi.org/10.1007/3-540-60364-6_28
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60364-1
Online ISBN: 978-3-540-45052-8
eBook Packages: Springer Book Archive