Abstract
The article criticises the attempt to establish connectionism as an alternative theory of human cognitive architecture through the introduction of thesymbolic/subsymbolic distinction (Smolensky, 1988). The reasons for the introduction of this distinction are discussed and found to be unconvincing. It is shown that thebrittleness problem has been solved for a large class ofsymbolic learning systems, e.g. the class oftop-down induction of decision-trees (TDIDT) learning systems. Also, the process of articulating expert knowledge in rules seems quite practical for many important domains, including common sense knowledge.
The article discusses several experimental comparisons betweenTDIDT systems and artificial neural networks using the error backpropagation algorithm (ANNs usingBP). The properties of one of theTDIDT systemsID3 (Quinlan, 1986a) are examined in detail. It is argued that the differences in performance betweenANNs usingBP andTDIDT systems reflect slightly different inductive biases but are not systematic; these differences do not support the view that symbolic and subsymbolic systems are fundamentally incompatible. It is concluded, that thesymbolic/subsymbolic distinction is spurious. It cannot establish connectionism as an alternative cognitive architecture.
This is a preview of subscription content, log in via an institution to check access.
References
Atlas, L, Cole, R., Connor, J., El-Sharkawi, M., Marks, R., Muthasamy, Y., and Barnard, E. (1990). ‘Performance Comparisons between Backpropagation Networks and Classification Trees on Three Real-World Applications’, in D. Touretzky, ed.,Advances in Neural Information Processing Systems, vol. 2, San Mateo, CA: Morgan Kaufmann Inc., pp. 622–29.
Breiman, L., Friedman, J. H., Olshen, R. A., and Stone, C. J. (1984),Classification and Regression Trees, Belmont: Wadsworth.
Cestnik, B., Kononenko, I., and Bratko, I. (1987), ‘ASSISTANT 86: A Knowledge Elicitation Tool for Sophisticated Users’, in I. Bratko and N. Lavrac, eds.,Progress in Machine Learning, Wilmslow: Sigma Press.
Crick, F. and Asanuma, C. (1986), ‘Certain Aspects of the Anatomy of the Cerebral Cortex’, in D. Rumelhart, J. McClelland, and the PDP Research Group,Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 2, Cambridge, MA: MIT Press, pp. 333–371.
Fisher, D. and McKusick, K. (1989), ‘An Empirical Comparison of ID3 and Back-Propagation’,Proceedings of the Eleventh International Joint Conference on Artificial Intelligence, pp. 788–793, Detroit, MI.
Fodor, J. A. and Pylyshyn, Z. (1988), ‘Connectionism and Cognitive Architecture: A Critical Analysis’, in S. Pinker and J. Mehler, eds.,Connections and Symbols, Cambridge, MA: MIT Press.
Kononenko, I., Bratko, I., and Roskar, E. (1984), ‘Experiments in Automatic Learning of Medical Diagnostic Rules’, technical report, Jozef Stefan Institute, Ljubljana, Slovenia.
Quinlan, R. (1986a), ‘Induction of Decision Trees’,Machine Learning 1, pp. 81–106.
Quinlan, R. (1986b), ‘Probabilistic Decision Trees’, in Kodratoff, Y. and Michalski, R., eds.,Machine Learning: An Artificial Intelligence Approach, vol. 3, pp. 140–52, San Mateo, CA, USA: Morgan Kaufmann, Inc.
Quinlan, R. (1989), ‘Unknown Attribute Values in Induction’, in B. Spatz, ed.,Proceedings of the Sixth International Workshop on Machine Learning, San Mateo, CA, USA: Morgan Kaufmann Publishers, Inc., pp. 164–68.
Quinlan, R., Compton, P., Horn, K., and Lazarus, L. (1987), ‘Inductive Knowledge Acquisition: A Case Study’, in R. Quinlan, ed.,Applications of Expert Systems, Sydney: Turing Institute Press in assoc. with Addison-Wesley Publishing Co.
Rumelhart, D., Hinton, G., and Williams, R. (1986), ‘Learning Internal Representations by Error Propagation’, in D. Rumelhart, J. McClelland, and the PDP Research Group,Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 1, Cambridge, MA: MIT Press, pp. 318–362.
Rumelhart, D., McClelland, J. and the PDP Research Group (1986),Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vols. 1 & 2, Cambridge, MA: MIT Press.
Shavlik, J., Mooney, R., and Towell, G. (1991), ‘Symbolic and Neural Learning Algorithms: An Experimental Comparison’,Machine Learning 6, pp. 111–143.
Schlimmer, J. (1987),Vote [Machine-readable data file], Adapted fromCongressional Quarterly Almanac, 98th Congress, 2nd session 1984, Volume XL: Congressional Quarterly Inc., Washington, D.C., 1985.
Smolensky, P. (1987), ‘The Constituent Structure of Connectionist Mental States: A Reply to Fodor and Pylyshyn’,The Southern Journal of Philosophy 26, pp. 137–161.
Smolensky, P. (1988), ‘On the Proper Treatment of Connectionism’,Behavioral and Brain Sciences 11, 1–74.
Weiss, S. and Kapouleas, I. (1989), ‘An Empirical Comparison of Pattern Recognition, Neural Nets, and Machine Learning Classification Methods’,Proceedings of the Eleventh International Joint Conference on Artificial Intelligence, pp. 688–693, Detroit, MI.
Wirth, J. & Catlett, J. (1988), ‘Experiments on the Costs and Benefits of Windowing in ID3’, in J. Laird, ed.,Proceedings of the Fifth International Conference on Machine Learning, pp. 87–99, San Mateo, CA, USA: Morgan Kaufmann Publishers, Inc.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Marinov, M.S. On the spuriousness of the symbolic/subsymbolic distinction. Mind Mach 3, 253–270 (1993). https://doi.org/10.1007/BF00976281
Issue Date:
DOI: https://doi.org/10.1007/BF00976281