Minds and Machines 4 (3):317-32 (1994)
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
|Keywords||Connectionism Epistemology Learning Metaphysics Representation|
|Categories||categorize this paper)|
References found in this work BETA
Connectionism and Cognitive Architecture.Jerry A. Fodor & Zenon W. Pylyshyn - 1988 - Cognition 28 (1-2):3-71.
Microcognition: Philosophy, Cognitive Science, and Parallel Distributed Processing.Andy Clark - 1991 - Cambridge: MIT Press.
Associative Engines: Connectionism, Concepts, and Representational Change.Andy Clark - 1993 - MIT Press.
Maturational Constraints on Language Learning.Elissa L. Newport - 1990 - Cognitive Science 14 (1):11-28.
Citations of this work BETA
Complexity and Individual Psychology.Yakir Levin & Itzhak Aharon - 2015 - Mind and Society 14 (2):203-219.
Similar books and articles
Two Great Problems of Learning.Nicholas Maxwell - 2003 - Teaching in Higher Education, 8 (January):129-134.
The Role of Representation in Connectionist Explanation of Cognitive Capacities.Robert C. Cummins - 1991 - In William Ramsey, Stephen P. Stich & D. Rumelhart (eds.), Philosophy and Connectionist Theory. Lawrence Erlbaum. pp. 91--114.
Superpositional Connectionism: A Reply to Marinov. [REVIEW]Andy Clark - 1993 - Minds and Machines 3 (3):271-81.
The Evolution of Learning: An Experiment in Genetic Connectionism.David Chalmers - 1992 - In Connectionist Models: Proceedings of the 1990 Summer School Workshop. Morgan Kaufmann.
Trading Spaces: Connectionism and the Limits of Uninformed Learning.Andy Clark & Chris Thornton - unknown
Added to index2009-01-28
Total downloads28 ( #181,785 of 2,163,570 )
Recent downloads (6 months)1 ( #348,040 of 2,163,570 )
How can I increase my downloads?