Abstract
A major battle between paradigms in cognitive science is underway. The last thirty years have been dominated by the classical view that human cognition is analogous to symbolic computation in digital computers. Connectionism proposes a different picture, inspired by the neural architecture of the brain: the mind is the result of the activity of immense numbers of simple units (akin to neurons) connected together in complex patterns or networks. On the classical account, information is represented by strings of symbols, just as we represent data in computer memory or (for that matter) on pieces of paper. The connectionist claims, on the other hand, that information is stored non-symbolically in the weights, or connection strengths, between the units of a neural net. The classicist believes that cognition resembles digital processing, where strings are produced in sequence according to the instructions of a (symbolic) program. The connectionist views mental processing as the dynamic and graded evolution of activity in a neural net, each unit’s activation depending on the connection strengths and activity of its neighbors, according to simple equations.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Ballard, D. H.: 1987, ‘Parallel Logical Inference and Energy Minimization’, Technical Report TR142, Computer Science Department, University of Rochester.
Bechtel, W.: 1988, ‘Connectionism and Rules and Representation Systems: Are They Compatible?’, Philosophical Psychology, 1, 5–15.
Churchland, P.: 1979, Scientific Realism and the Plasticity of Mind, Cambridge University Press, New York.
Cummins, R.: 1989, Meaning and Mental Representation, MIT Press, Cambridge, MA.
Cummins, R.: (forthcoming), ‘The Role of Representation in Connectionist Explanations of Cognitive Capacities’, in Ramsey, Rummelhart and Stich (forthcoming).
Elman, J.: 1988, ‘Finding Structure in Time’, Technical Report CRL 8801, Center for Research in Language, UCSD.
Elman, J.: 1989, ‘Representation and Structure in Connectionist Models’, Technical Report CRL 8903, Center for Research in Language, UCSD.
Engel, R.: 1989, ‘Matters of Degree’, Journal of Philosophy, 23–37.
Fanty, M.: 1985, ‘Context-Free Parsing in Connectionist Networks’, Technical Report TR-174, Department of Computer Science, University of Rochester.
Fodor, J. and Pylyshyn, Z.: 1988, ‘Connectionism and Cognitive Architecture: A Critical Analysis’, Cognition, 28, 3–71.
Hanson, J. and Kegl, J.: 1987, ‘PARSNIP: A Connectionist Network that Learns Natural Language Grammar from Exposure to Natural Language Sentences’, Ninth Annual Conference of the Cognitive Science Society, pp. 106–119.
Hawthorne, J.: 1989, ‘On the Compatibility of Connectionist and Classical Models’, Philosophical Psychology, 2, 5–15.
Hinton, G.: 1988, ‘Representing Part-Whole Hierarchies in Connectionist Networks’, The Tenth Annual Conference of the Cognitive Science Society, 1988, 48–54.
Hinton, G. and Anderson, J., eds.: 1981, Parallel Models of Associative Memory, Erlbaum, Hillsdale, NJ.
Hinton, G., McClelland, J. and Rumelhart, D.: 1986, ‘Distributed Representations’, Chapter 3 of Rumelhart, McClelland, et al.
Hinton, G. and Sejnowski, T.: 1986, ‘Learning and Relearning in Boltzmann Machines’, Chapter 7 of Rumelhart, McClelland, et al.
Horgan, T. and Tienson, J.: 1989, ‘Representations without Rules’, Philosophical Topics, 15.
Jordan, M.: 1986, ‘Serial Order: A Parallel Distributed Processing Approach’, Technical Report ICS-8604, UCSD.
Kirsh, D.: 1987, ‘Putting a Price on Cognition’, The Southern Journal of Philosophy, 26, Supplement, 119–135.
Kirsh, D.: (forthcoming), ‘When is Information Explicitly Represented?’, to appear in Information Thought and Content, P. Hanson,, UBC Press.
Marr, D.: 1982, Vision, Freeman, San Francisco.
McClelland, J. and Elman, J.: 1986, ‘The TRACE Model of Speech Perception’, Cognitive Psychology, 18, 1–86.
McClelland, J. and Rumelhart, D.: 1986, ‘A Distributed Model of Human Learning and Memory’, Chapter 17 of McClelland, Rumelhart, et al.
McClelland, J., Rumelhart, D., et al.: 1986, Parallel Distributed Processing, II, MIT Press, Cambridge, MA.
Metcalf Eich, J.: 1985, ‘Levels of Processing, Encoding Specificity, Elaboration, and CHARM’, Psychological Review, 92, 1–38.
Pollack, J.: 1988, ‘Recursive Auto-Associative Memory: Devising Compositional Distributed Representation’, Technical Report MCCS-88-124, Computing Research Laboratory, New Mexico State University.
Ramsey, W., Rumelhart, D. and Stich, S.: (forthcoming), Philosophy and Connectionist Theory, Erlbaum, Hillsdale, NJ.
Ramsey, W., Stich, S. and Garon, J.: (forthcoming), ‘Connectionism, Eliminitivism, and the Future of Folk Psychology’, to appear in Ramsey, Rumelhart and Stich (forthcoming).
Rumelhart, D., McClelland, J., and the PDP Research Group: 1986, Parallel Distributed Processing, I, MIT Press, Cambridge, MA.
Servan-Schreiber, D., Cleeremans, A. and McClelland, J.: 1988, ‘Encoding Semantical Structure in Simple Recurrent Nets’, Technical Report CMU-CS-88-183, Department of Computer Science, Carnegie Mellon University, also in Advances in Neural Information Processing Systems I, D. Touretzky, (ed.), (pp. 643–652), William Kaufmann, Inc., Los Altos, CA.
Shieber, S.: 1986, An Introduction to Unification-Based Approaches to Grammar, Center for the Study of Language and Information, Stanford.
Smolensky, P.: 1988, ‘On the Proper Treatment of Connectionism’, Behavioral and Bruin Sciences, 11, 1–74.
Smolensky, P.: 1987, ‘On Variable Binding and the Representation of Symbolic Structures in Connectionist Systems’, Technical Report CU-CS-355-87, Department of Computer Science, University of Colorado at Boulder.
Smolensky, P.: 1986, ‘Neural and Conceptual Interpretation of PDP Models’, Chapter 22 of McClelland, Rumelhart, and PDP Research Group (1986).
Touretzky, D.: 1986, ‘BoltzCONS: Reconciling Connectionism with the Recursive Nature of Stacks and Trees’, Eighth Annual Conference of the Cognitive Science Society, 522–530.
Touretzky, D. and Geva, S.: 1987, ‘A Distributed Connectionist Representation for Concept Structures’, Ninth Annual Conference of the Cognitive Science Society, 155–164.
Touretzky, D. and Hinton, G.: 1985, ‘Symbols Among the Neurons: Details of a Connectionist Inference Architecture,’ Proceedings of the Ninth International Joint Conference on Artificial Intelligence.
van Gelder, T.: 1990, ‘Compositionality: A Connectionist Variation on a Classical Theme’, Cognitive Science 14, 355–384.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1991 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Garson, J.W. (1991). What Connectionists Cannot Do: The Threat to Classical AI. In: Horgan, T., Tienson, J. (eds) Connectionism and the Philosophy of Mind. Studies in Cognitive Systems, vol 9. Springer, Dordrecht. https://doi.org/10.1007/978-94-011-3524-5_6
Download citation
DOI: https://doi.org/10.1007/978-94-011-3524-5_6
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-010-5559-8
Online ISBN: 978-94-011-3524-5
eBook Packages: Springer Book Archive