Abstract
The paper considers the problems involved in getting neural networks to learn about highly structured task domains. A central problem concerns the tendency of networks to learn only a set of shallow (non-generalizable) representations for the task, i.e., to ‘miss’ the deep organizing features of the domain. Various solutions are examined, including task specific network configuration and incremental learning. The latter strategy is the more attractive, since it holds out the promise of a task-independent solution to the problem. Once we see exactly how the solution works, however, it becomes clear that it is limited to a special class of cases in which (1) statistically driven undersampling is (luckily) equivalent to task decomposition, and (2) the dangers of unlearning are somehow being minimized. The technique is suggestive nonetheless, for a variety of developmental factors may yield the functional equivalent of both statistical AND ‘informed’ undersampling in early learning.
Similar content being viewed by others
References
Bechtel, W. and Abrahamsen, A. (1991),Connectionism and the Mind, Oxford: Basil Blackwell.
Clark, A. (1989),Microcognition: Philosophy, Cognitive Science and Parallel Distributed Processing, Cambridge, MA: MIT Press/Bradford Books.
Clark, A. (1991), ‘In Defence of Explicit Rules’, in W. Ramsey, S. Stich, and D. Rumelhart, eds.,Philosophy and Connectionist Theory, New Jersey: Erlbaum.
Clark, A. and Karmiloff-Smith, A. (in press), ‘The Cognizer's Innards: A Psychological and Philosophical Perspective on the Development of Thought’,Mind and Language.
Clark, A. (1993),Associative Engines: Connectionism, Concepts and Representational Change, Cambridge, MA: MIT Press/Bradford Books.
Cooper, R. and Franks, B. (1991), Interruptability: A New Constraint on Hybrid Systems, inAISB Quarterly (Newsletter of the Society for the Study of Artificial Intelligence and Simulation of Behaviour) (Autumn/Winter 1991) pp. 25–30.
Dennett, D. (1991), ‘Mother Nature versus the Walking Encyclopedia’, in W. Ramsey, S. Stich, and D. Rumelhart, eds.,Philosophy and Connectionist Theory, Hillsdale, NJ.: Erlbaum, pp. 21–30.
Elman J. (1991a), ‘Incremental Learning or the Importance of Starting Small,’ Technical Report 9101, Center for Research in Language, University of California, San Diego.
Elman, J. (1991b), ‘Distributed Representations, Simple Recurrent Networks and Grammatical Structure,’Machine Learning 7, pp. 195–225.
Finch, S. and Chater, N. (1991), ‘A Hybrid Approach to the Automatic Learning of Linguistic Categories,AISB Quarterly (Autumn/Winter, 1991), pp. 16–24.
Fodor, J. and Pylyshyn, Z. (1988), Connectionism and Cognitive Architecture. A Critical Analysis,Cognition 28, pp. 3–71.
French, R. M. (1991), ‘Using Semi-distributed Representations to Overcome Catastrophic Forgetting in Connectionist Networks,’ CRCC Technical Report 51, University of Indiana, Bloomington, Indiana 47408.
French, R. M. (1992), ‘Semi-distributed Representations and Catastrophic Forgetting in Connectionist Networks,Connection Science 4, pp. 365–377.
Gonzalez, R. and Wintz, P. (1977),Digital Image Processing, Reading, MA: Addison-Wesley.
Hayes, P. (1985), ‘The Second Naive Physics Manifesto,’ in J. Jobbs and R. Moore, eds.,Formal Theories of the Commonsense World, Ablex, New Jersey.
Newport, E. (1988), ‘Constraints on Learning and their Role in Language Acquisition: Studies of the Acquisition of American Sign Language,’Language Sciences 10, pp. 147–172.
Newport, E. (1990), ‘Maturational Constraints on Language Learning’,Cognitive Science 14, pp. 11–28.
Norris, D. (1990), ‘How to Build a Connectionist Idiot (Savant)’,Cognition 35, pp. 277–291.
Norris, D. (1991), ‘The Constraints on Connectionism,’The Psychologist,4, pp. 293–296.
Plunkett, K. and C. Sinha (1991), ‘Connectionism and Developmental Theory,’Psykologisk Skriftserie Aarhus 16, pp. 1–77.
Thornton, C. (1991), ‘Why Connectionist Learning Algorithms Need to be More Creative’, Conference Preprints for the First Symposium on Artificial Intelligence, Reasoning and Creativity (University of Queensland, August 1991). Also CSRP 218, Cognitive Science Research Paper, University of Sussex.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Clark, A. Representational trajectories in connectionist learning. Mind Mach 4, 317–332 (1994). https://doi.org/10.1007/BF00974197
Issue Date:
DOI: https://doi.org/10.1007/BF00974197