Two Apparent ‘Counterexamples’ To Marcus: A Closer Look
Marcus et al.’s experiment (1999) concerning infant ability to distinguish between differing syntactic structures has prompted connectionists to strive to show that certain types of neural networks can mimic the infants’ results. In this paper we take a closer look at two such attempts: Shultz and Bale [Shultz, T.R. and Bale, A.C. (2001), Infancy 2, pp. 501–536] Altmann and Dienes [Altmann, G.T.M. and Dienes, Z. (1999) Science 248, p. 875a]. We were not only interested in how well these two models matched the infants’ results, but also whether they were genuinely learning the grammars involved in this process. After performing an extensive set of experiments, we found that, at first blush, Shultz and Bale’s model (2001) replicated the infant’s known data, but the model largely failed to learn the grammars. We also found serious problems with Altmann and Dienes’ model (1999), which fell short of matching any of the infant’s results and of learning the syntactic structure of the input patterns.
Keywords:artificial grammars connectionism grammar learning neural networks simple recurrent networks syntactic structures
simple recurrent network
Unable to display preview. Download preview PDF.
- Christiansen, M.H. and Curtin, S.L. (1999), ‘The Power of Statistical Learning: No Need for Algebraic Rules’, in Proceedings of the 21st Annual Conference of the Cognitive Science Society, pp. 114–119Google Scholar
- Christiansen, M.H., Conway, C.M., and Curtin, S.L. (2001), ‘A Connectionist Single-mechanism Account of Rule-like Behavior in Infancy’, in Proceedings of the 22nd Annual Conference of the Cognitive Science Society, pp. 83–88Google Scholar
- Elman, J.L. (1999), Generalization, rules, and neural networks: A simulation of Marcus et al. www.crl.ucsd.edu/∼ ∼elman/Papers/MVRVsim.html Google Scholar
- Fahlman S.E., Labiere C. (1990) The Cascade-correlation learning architecture. Advances in Neural Information Processing Systems 2:524–532Google Scholar
- Marcus, G.F. (2001), The Algebraic Mind, The MIT PressGoogle Scholar
- Shultz, T.R. (1999), ‘Rule Learning by Habituation can be Simulated in Neural Networks’, in Proceedings of the 21st Annual Conference of the Cognitive Science Society, pp. 665–670Google Scholar
- Vilcu, M., and Hadley, R.F. (2001), ‘Generalization in Simple Recurrent Networks’, Proceedings of the 23rd Annual Conference of the Cognitive Science Society, pp. 1072–1077Google Scholar