Skip to main content
Log in

The allure of connectionism reexamined

  • Published:
Synthese Aims and scope Submit manuscript

Abstract

There is currently a debate over whether cognitive architecture is classical or connectionist in nature. One finds the following three comparisons between classical architecture and connectionist architecture made in the pro-connectionist literature in this debate: (1) connectionist architecture is neurally plausible and classical architecture is not; (2) connectionist architecture is far better suited to model pattern recognition capacities than is classical architecture; and (3) connectionist architecture is far better suited to model the acquisition of pattern recognition capacities by learning than is classical architecture. If true, (1)–(3) would yield a compelling case against the view that cognitive architecture is classical, and would offer some reason to think that cognitive architecture may be connectionist. We first present the case for (1)–(3) in the very words of connectionist enthusiasts. We then argue that the currently available evidence fails to support any of (1)–(3).

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Atlas, L., Cole, R., Muthsamy, Y., Lippman, A., Conner, J., Park, D., El-Sharkawi, M. and Marks III, R.J.: 1990, ‘A Performance Comparison of Trained Multi-Layered Perceptrons and Trained Classification Trees’,Proceedings of IEEE 78, 1614–9.

    Google Scholar 

  • Atlas, L., Cole, R., Conner, J., Elasharkawi, M., Marks III, R.J., Muthisamy, Y. and Barnard, E.: 1990, ‘Performance Comparisons Between Back-Propagation Networks and Classification Trees on Three Real-World Applications’,Advances in Neural Information Processing, Volume II, Morgan Kaufmann, San Mateo, California.

    Google Scholar 

  • Baase, S.: 1991,Computer Algorithms: Introduction to Design and Analysis.

  • Bareis, E. R.: 1989,Exemplar-Based Knowledge Acquisition: A Unified Approach to Concept Representation, Classification, and Learning, Academic Press, Boston.

    Google Scholar 

  • Beale, R. and Jackson, T.: 1990,Neural Computing: An Introduction, Adam Hilgar.

  • Bechtel, W.: 1991, ‘Connectionism and the Philosophy of Mind: An Overview’, in Horgan and Tienson (eds.).

  • Bechtel, W.: 1993, ‘The Case for Connectionism’,Philosophical Studies 70, 119–54.

    Google Scholar 

  • Bechtel, W. and Abrahamsen, A.: 1991,Connectionism and the Mind: An Introduction to Parallel Processing in Networks, Basil Blackwell, Cambridge.

    Google Scholar 

  • Bratko, I. and Kononenko, I.: 1987, ‘Learning Diagnostic Rules From Incomplete and Noisy Data’, in B. Phelps (ed.),Interactions in AI and Statistical Methods, Technical Press.

  • Breiman, L., Freidman, J.H., Olshen, R. A. and Stone, C. J.: 1984,Classification and Regression Trees, Wadsworth, Belmont, California.

  • Breiman, L., Friedman, J.: 1988, ‘Comments on “Tree-Structured Classification via Generalized Discriminant Analysis”’,American Statistical Association 83, 725–7.

    Google Scholar 

  • Cestnik, B., Kononenko, I. and Bratko, I.: 1986, ‘Assistant 86: A Knowledge Elicitation Tool for Sophisticated Users’, in Bratko and N. Lavrac (eds.),Progress in Machine Learning, Sigma Press.

  • Chater, N. and Oaksford M.: 1990, ‘Autonomy, Implementation, and Cognitive Architecture: A Reply to Fodor and Pylyshyn’,Cognition 34, 93–107.

    Google Scholar 

  • Cheng, J., Fayyad, U. M., Irani, K. B. and Qian, Z.: 1988, ‘Improved Decision Trees: A Generalized Version of ID3’,Proceedings of the Fifth International Conference on Machine Learning, pp. 100–6.

  • Churchland, P. M.: 1989,A Neuro-Computational Perspective, MIT/Bradford Press, Cambridge, Massachusetts.

    Google Scholar 

  • Churchland, P. S. and Sejnowski, T. J.: 1990, ‘Neural Representation and Neural Computation’,Philosophical Perspectives 4, 343–82.

    Google Scholar 

  • Clark, A.: 1988,Microcognition, MIT/Bradford Press, Cambridge, Massachusetts.

    Google Scholar 

  • Clark, A.: 1993, ‘Superpositional Connectionism: A Reply to Marinov’,Mind and Machines 3, 271–81.

    Google Scholar 

  • Crawford, S. L.: 1989, ‘Extensions to the CART Algorithm’,International Journal of Man-Machine Studies 31, 197–217.

    Google Scholar 

  • Crick, F. and Asanuma, C.: 1986, ‘Certain Aspects of the Anatomy and Physiology of the Cerebral Cortex’, in Rumelhart and McClelland (eds.),2, 332–71.

  • Dattatreya, G. R., Kanal, L. N.: 1985, ‘Decision Trees in Pattern Recognition’, in Kanal and Rosenfield (eds.),Progress in Pattern Recognition, Vol. 2, Elsevier/North-Holland, Amsterdam.

    Google Scholar 

  • Dennett, D.: 1991, ‘Mother Nature Versus the Walking Encyclopedia: A Western Drama’, in Ramsey, Stich and Rumelhart (eds.), pp. 21–30.

  • Detrano, R.: manuscript, ‘International Application of a New Probability Algorithm for the Diagnosis of Coronary Artery Disease’.

  • Dietterich, T. G., Hild, H. and Bakiri, G.: 1990, ‘A Comparative Study of ID3 and Backpropagation for English Text-to-Speech Mapping’,Proceedings of the Seventh International Conference on Machine Learning, pp. 24–31.

  • Dretske, F.: 1985, ‘Mentality and Machines’,Proceedings and Addresses of the American Philosophical Association 59.

  • Dyer, M.: 1991, ‘Connectionism Versus Symbolism in High-Level Cognition’, in Horgan and Tienson (eds.), pp. 382–416.

  • Feldman, J. A. and Ballard, D. H.: 1982, ‘Connectionist Models and Their Properties’, Cognitive Science6,, 205–54.

    Google Scholar 

  • Fetzer, J.: 1991, ‘Series Preface’, in Horgan and Tienson (eds.), p. ix.

  • Fisher, D. and McKusick, K. B.: 1989, ‘An Empirical Comparison of ID3 and Back-Propagation’,Proceedings of the Eleventh International Joint Conference on Artificial Intelligence, pp. 788–93.

  • Fisher, D., McKusick, K., Mooney, R., Shavlik, J. and Towell, G.: 1989, ‘Processing Issues in Comparisons of Symbolic and Connectionist Learning Systems’,Proceedings of the Sixth Workshop on Machine Learning, pp. 169–173.

  • Fisher, D. and Schlimmer, J.: 1988, ‘Concept Simplification and Predication Accuracy’,Proceedings of the Fifth International Machine Learning Conference.

  • Fodor, J. and Pylyshyn, Z.: 1988, ‘Connectionism and Cognitive Architecture: A Critical Analysis’,Cognition 28, 3–71.

    Google Scholar 

  • Fodor, J. and McLaughlin, B.: 1990, ‘Connectionism and the Problem of Systematicity: Why Smolensky's Solution Doesn't Work’,Cognition 35, 183–204.

    Google Scholar 

  • Frankin, S. and Garzon, M.: manuscript, ‘Neural Network Implementation of Turing Machines’.

  • Friedman, J. H.: 1973, ‘A Recursive Partitioning Decision Rule for Nonparametric Classification’,IEEE Transactions Computing C-26, 404–8.

    Google Scholar 

  • Gelfand, S. B. and Delp, E. J.: 1991, ‘On Tree Structured Classifiers’, in Sethi and Jain (eds.), pp. 51–70.

  • Golea, M. and Marchland, M.: 1990, ‘A Growth Algorithm for Neural Network Decision Trees’,Europhysics Letters 12, 205–10.

    Google Scholar 

  • Goodman, R. M. and Smyth, P.: 1988, ‘Decision Tree Design from a Communication Theory Standpoint’,IEEE Transactions Information Theory 34, 979–94.

    Google Scholar 

  • Haugeland, J.: 1985,Artificial Intelligence: The Very Idea, MIT/Bradford Press, Cambridge, Massachusetts.

    Google Scholar 

  • Henrichon, E. G. and Fu, K. S.: 1969, ‘A Nonparametric Partitioning Procedure for Pattern Classification’,IEEE Transactions Computing C-18, 614–24.

    Google Scholar 

  • Hillis, D.: 1985,The Connection Machine, MIT/Bradford Press, Cambridge, Massachusetts.

    Google Scholar 

  • Horgan, T. and Tienson, J. (eds.): 1991,Connectionism and the Philosophy of Mind, Kluwer Academic Publishers, Dordrecht.

    Google Scholar 

  • Hunt, E. B., Marin, J. and Stone, P. J.: 1966,Experiments in Induction, Academic Press, Boston.

    Google Scholar 

  • Kanal, L. N.: 1979, ‘Problem-Solving Models and Search Strategies for Pattern Recognition’,IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-1, 194–201.

    Google Scholar 

  • Kononenko, I., Bratko, I. and Roskar, E.: 1986, ‘ASSISTANT: A System for Inductive Learning’,Informatica 10.

  • Koutsougeras, C. and Papachristou, C. A.: 1989, ‘Training of a Neural Network for Pattern Classification Based on an Entropy Measure’,Proceedings IEEE International Conference on Neural Networks, Vol. I, San Diego, California, pp. 247–54.

  • Maloney, J. C.: 1991, ‘Connectionism and Conditioning’, in Horgan and Tienson (eds.), pp. 167–197.

  • Marinov, M. S.: 1993, ‘On the Spuriousness of the Symbolic/Subsymbolic Distinction’,Minds and Machines 3,, 253–70.

    Google Scholar 

  • McClelland, J. and Rumelhart, D.: 1986, ‘Introduction to Part V’, in D. Rumelhart and D. McClelland (eds.), Vol. II.

  • McClelland, J., Rumelhart, D. and Hinton, G.: 1986, ‘The Appeal of Parallel Distributed Processing’, in D. Rumelhart and D. McClelland (eds.), Vol. I.

  • McLaughlin, B.: 1987, ‘Tye on Connectionism’,Southern Journal of Philosophy 26, Spindel Conference on Connectionism, pp. 185–193.

  • McLaughlin, B.: 1993a, ‘The Connectionism/Classicism Battle to Win Souls’,Philosophical Studies 70, 45–72.

    Google Scholar 

  • McLaughlin, B.: 1993b, ‘Systematicity, Conceptual Truth, and Evolution’, in C. Hookway and D. Peterson (eds.),Royal Institute of Philosophy, Supplement, No. 34, reprinted in C. Hookway and D. Peterson (eds.),Philosophy and Cognitive Science, Cambridge, Cambridge University Press, pp. 217–34.

    Google Scholar 

  • Minsky, M. and Papert, S.: 1988,Perceptrons, expanded edition, MIT/Bradford Press, Cambridge, Massachusetts.

    Google Scholar 

  • Mooney, R., Shavlik, J. Towell, G. and Gove, A.: 1989, ‘An Experimental Comparison of Symbolic and Connectionist Learning Algorithms’,Proceedings of the Eleventh International Joint Conference on Artificial Intelligence, pp. 775–70.

  • Nadel, L., Cooper, L. A., Culicover, P. and Harnish, R. M.: 1989,Neural Connections. Mental Computation, MIT/Bradford Press, Cambridge, Massachusetts.

    Google Scholar 

  • Patterson, A. and Niblett, T.: 1983,ACLS User Manual, Intelligent Terminal Ltd, Glasgow.

    Google Scholar 

  • Payne, H. J. and Meisel, W. S.: 1977, ‘An Algorithm for Constructing Optimal Binary Decision Trees’,IEEE Transactions Computing C-26, 1905–16.

    Google Scholar 

  • Pazzani, M. and Dyer, M.: 1987, ‘A Comparison of Concept Identification in Human Learning and Network Learning with Generalized Delta Rule’,Proceedings of the Tenth International Joint Conference on Artificial Intelligence, pp. 147–50.

  • Pylyshyn, Z.: 1984,Computation and Cognition, MIT/Bradford Press, Cambridge, Massachusetts.

    Google Scholar 

  • Quinlan, J. R.: 1979, ‘Discovering Rules by Induction from Large Collections of Examples’, in D. Michie (ed.),Expert Systems in the Micro Electronic Age, Edinburgh University Press.

  • Quinlan, J. R.: 1986a, ‘Induction of Decision Trees’,Machine Learning 1, 81–106.

    Google Scholar 

  • Quinlan, J. R.: 1986b, ‘Probabilistic Decision Trees’, in Y. Kodratoff and R. Michalski (eds.),Machine Learning: An Artificial Intelligence Approach 3, Morgan Kaufman, San Mateo, California, pp. 140–52.

    Google Scholar 

  • Quinlan, J. R.: 1987a, ‘Decision Trees as Probabilistic Classifiers’,Proceedings of the Fourth International Machine Learning Workshop, Irvine California, pp. 31–7.

  • Quinlan, J. R.: 1987b, ‘Simplifying Decision Trees’,International Journal of Man-Machine Studies 27, 221–34.

    Google Scholar 

  • Quinlan, J. R.: 1987c, ‘Generating Production Rules from Decision Trees’,Proceedings of 10th International Joint Conference on Artificial Intelligence, pp. 304–7.

  • Quinlan, J. R.: 1988, ‘An Empirical Comparison of Genetic and Decision-Tree Classifiers’,Proceedings of the 5th International Machine Learning Conference.

  • Quinlan, J. R.: 1989, ‘Unknown Attribute Values in Induction’Proceedings of the Sixth International Workshop on Machine Learning, pp. 164–8.

  • Quinlan, J. R. and Rivest, R. L.: 1989, ‘Inferring Decision Trees Using Minimum Description Length Principle’,Information and Computation 80, 227–248.

    Google Scholar 

  • Reinke, R.: 1984,Knowledge Acquisition and Refinement Tools for the ADVISE Meta-Expert System, Master's thesis, Department of Computer Science, University of Illinois.

  • Rey, G.: 1991, ‘An Explanatory Budget for Connectionism and Eliminativism’, in Horgan and Tienson (eds.), pp. 219–40.

  • Rumelhart, D.: 1992, ‘Towards a Micro-Structural Account of Human Reasoning’, in S. Davis (ed.),Connectionism: Theory and Practice, Oxford University Press, New York, pp. 69–83.

    Google Scholar 

  • Rumelhart, D., McClelland, J. and the PDP Research Group: 1986,Parallel Distributed Processing: Explorations in the Microstructure of Cognition, 2 Vols., MIT Press, Cambridge, Massachusetts.

    Google Scholar 

  • Schlimmer, J. and Fisher D.: 1986, ‘A Case Study of Incremental Concept’,Proceedings of the Sixth National Conference on Artificial Intelligence.

  • Sejnowski, T. J. and Rosenberg, C.: 1987, ‘Parallel Networks that Learn to Pronounce English Text’,Complex Systems 1, 145–68.

    Google Scholar 

  • Sethi, I. K. and Savaraydu, G. P. R.: 1981, ‘Hierarchical Classifier Design Using Mutual Information’,IEEE Transaction Pattern Analysis and Machine Intelligence PAMI-4, 441–5.

    Google Scholar 

  • Sethi, I. K.: 1990, ‘Entropy Nets: From Decision Trees to Neural Networks’,Proceedings IEEE 78, 1605–713.

    Google Scholar 

  • Sethi, I. K. and Jain, A. K. (eds.): 1991,Artificial Neural Networks and Statistical Pattern Recognition, Elsevier Science Publishers/North-Holland, Amsterdam.

    Google Scholar 

  • Sethi, I. K.: 1991, ‘Decision Tree Performance Enchancement Using Artificial Neural Network Implementation’, in Sethi and Jain (eds.), pp. 71–88.

  • Shapiro, A.: 1987,Structured Induction in Expert Systems, Addison-Wesley, Reading, Massachusetts.

    Google Scholar 

  • Shavlik, J., Mooney R. and Towell, G.: 1991, ‘Symbolic and Neural Learning Algorithms: An Experimental Comparison’,Machine Learning 6, 111–43.

    Google Scholar 

  • Shannon, L. R.: 1993, ‘Ways to Think About Computing’,The New York Times, Section C, p. 7.

  • Sklansky, J.: 1980, ‘Locally Trained Piecewise Linear Classifiers’,IEEE Transaction Pattern Analysis and Machine Intelligence PAMI-2, 101–11.

    Google Scholar 

  • Smolensky, P.: 1988, ‘On the Proper Treatment of Connectionism’,Behavioral and Brain Sciences 11, 1–74.

    Google Scholar 

  • Smolensky, P.: 1989, ‘Connectionist Modeling: Neural Computation/Mental Connections’, in Nadel et al. (eds).

    Google Scholar 

  • Sterelny, K.: 1990,The Representational Theory of the Mind, Basil Blackwell, Oxford.

    Google Scholar 

  • Swain, P. H. and Hauska, H.: 1977, ‘The Decision Tree Classifier: Design and Potential’,IEEE Trans. Geosc. Electron GE-15, 142–7.

    Google Scholar 

  • Tienson, J.: 1991, ‘Introduction’, in Horgan and Tienson (eds.), pp. 1–29.

  • Touretsky, D. S. and Hinton, G. E.: 1988, ‘A Distributed Connectionist Production System’,Cognitive Science 12, 423–66.

    Google Scholar 

  • Utgoff, P.: 1988, ‘ID5: An Incremental ID3’,Proceeding of the Fifth International Machine Learning Conference.

  • Utgoff, P.: 1989, ‘Incremental Design of Decision Trees’,Machine Learning 4, 161–186.

    Google Scholar 

  • Van Gelder, T.: 1991, ‘What is the ‘D’ in PDP?: A Survey of the Coincept of’, in W. Ramsey, S. Stich and D. Rumelhart (eds.),Philosophy and Connectionist Theory, Lawrence Erlbaum Associates, Hillsdale, New Jersey, pp. 33–59.

    Google Scholar 

  • Warfield, T. A.: forthcoming, ‘Review of Horgan's and Tienson's Connectionism and the Philosophy of Mind’ inMinds and Machines.

  • Weiss, S. M. 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. 781–7.

  • Werbos, P. J.: 1991, ‘Links Between Artificial Neural Networks (ANN) and Statistical Pattern Recognition’, in Sethi and Jain (eds.), pp. 11–31.

  • Wirth, J, Catlett, J. and Laird, J. (eds.): 1988, ‘Experiments on the Costs and Benefits of Windowing in ID3’,Proceedings of the Fifth International Conference on Machine Learning, San Mateo, California., pp. 87–99.

Download references

Author information

Authors and Affiliations

Authors

Rights and permissions

Reprints and permissions

About this article

Cite this article

McLaughlin, B.P., Warfield, T.A. The allure of connectionism reexamined. Synthese 101, 365–400 (1994). https://doi.org/10.1007/BF01063895

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF01063895

Keywords

Navigation