Abstract
In 1988, Smolensky proposed that connectionist processing systems should be understood as operating at what he termed the `subsymbolic' level. Subsymbolic systems should be understood by comparing them to symbolic systems, in Smolensky's view. Up until recently, there have been real problems with analyzing and interpreting the operation of connectionist systems which have undergone training. However, recently published work on a network trained on a set of logic problems originally studied by Bechtel and Abrahamsen (1991) seems to offer the potential to provide a detailed, empirically based answer to questions about the nature of subsymbols. In this paper, a network analysis procedure and the results obtained using it are discussed. This provides the basis for an insight into the nature of subsymbols, which is surprising.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Bechtel, W. and Abrahamsen, A. (1991), Connectionism and the Mind, Cambridge, MA: Basil Blackwell.
Berkeley, I., Dawson, M., Medler, D., Schopflocher, D. and Hornsby, L. (1995), Density plots of hidden unit activations reveal interpretable dands, Connection Science 7, pp. 167-186.
Clark, A. (1993), Associative Engines: Connectionism. Concepts, and Representational Change, Cambridge, MA: MIT Press.
Dawson, M. (1998), Understanding Cognitive Science, Oxford: Blackwells.
Dawson, M. and Schopflocher, D. (1992), ‘Modifying the Generalized Delta Rule to Train Networks of Non-Monotonic Processors for Pattern Classification’, Connection Science 4/1, pp. 19-31.
Fodor, J. (1991), ‘A Reply to Smolensky’ in Loewer, B. and Rey, G. (eds.), Meaning in Mind: Fodor and His Critics, Oxford: Blackwells, p. 310.
Fodor, J. (1997), ‘Connectionism and the Problem of Systematicity (continued): Why Smolensky's Solution Still Doesn't Work’, Cognition 62, pp. 109-119.
Fodor, J. and McLaughlin (1990), ‘Connectionism and the Problem of Systematicity: Why Smolensky's Solution Doesn't Work’, Cognition 35, pp. 183-204.
Fodor, J. and Pylyshyn, Z. (1988), ‘Connectionism and Cognitive Architecture: A Critical Analysis’, Cognition 28, pp. 3-71.
Hanson, S. and Burr, D. (1990), ‘What Connectionist Models Learn: Learning and Representation in Connectionist Networks’, Behavioral and Brain Science 13, pp. 471-518.
McCaughan, D., Medler, D. and Dawson, M. (1999), ‘Internal Representation in Networks of Non-Monotonic Processing Units’, in The Proceedings of the International Joint Conference on Neural Networks, Washington, D.C., June 1999.
McCloskey, M. (1991), ‘Networks and Theories: The Place of Connectionism in Cognitive Science’ Psychological Science 2(6), pp. 387-395.
Mozer, M. and Smolensky, P. (1989), ‘Using Relevance to Reduce Network Size Automatically’ Connection Science 1, pp. 3-16.
Newell, A. and Simon, H. (1976), ‘Computer Science as Empirical Inquiry: Symbols and Search’, Communications of the ACM 19(3), pp. 113-126.
Robinson, D. (1992), ‘Implications of Neural Networks for How We Think about Brain Function’, Behavioral and Brain Science 15, pp. 644-655.
Schneider, W. (1987), ‘Connectionism: Is it a Paradigm Shift for Psychology?’ Behaviour Research Methods, Instruments & Computers 19(2), pp. 73-83.
Smolensky, P. (1988), ‘On the Proper Treatment of Connectionism’, in Behavioral and Brain Sciences, 11, pp. 1-74.
Smolensky, P. (1991), ‘Connectionism, Constituency, and the Language of Thought’ in Loewer, B. and Rey, G. (eds.), Meaning in Mind: Fodor and His Critics, Oxford: Blackwells, pp. 201-227.
Smolensky, P. (1995), ‘Reply: Constituent Structure and Explanation in an Integrated Connectionist/Symbolic Cognitive Architecture’, in C. MacDonald and G. MacDonald (eds.), Connectionism: Debates in Psychological Explanation, Oxford: Blackwells, pp. 223-290.
Van Gelder, T. (1990), ‘Compositionality: A Connectionist Variation on a Classical Theme’, Cognitive Science 14, pp. 355-384.
Rights and permissions
About this article
Cite this article
Berkeley, I.S.N. What the #$*%! is a Subsymbol?. Minds and Machines 10, 1–14 (2000). https://doi.org/10.1023/A:1008329513803
Issue Date:
DOI: https://doi.org/10.1023/A:1008329513803