Minds and Machines 4 (3):317-32 (1994)
|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|
|Keywords||Connectionism Epistemology Learning Metaphysics Representation|
|Categories||categorize this paper)|
|Through your library||Configure|
Similar books and articles
Nicholas Maxwell (2003). Two Great Problems of Learning. Teaching in Higher Education, 8 (January):129-134.
Robert C. Cummins (1991). The Role of Representation in Connectionist Explanation of Cognitive Capacities. In William Ramsey, Stephen P. Stich & D. Rumelhart (eds.), Philosophy and Connectionist Theory. Lawrence Erlbaum.
Frank C. Keil (2008). How to Learn Multiple Tasks. Biological Theory 3 (1).
Andy Clark (1993). Superpositional Connectionism: A Reply to Marinov. [REVIEW] Minds and Machines 3 (3):271-81.
Susan Hanson & D. Burr (1990). What Connectionist Models Learn. Behavioral and Brain Sciences.
David Chalmers (1992). The Evolution of Learning: An Experiment in Genetic Connectionism. In Connectionist Models: Proceedings of the 1990 Summer School Workshop. Morgan Kaufmann.
Chris Thornton & Andy Clark (1997). Relational Learning Re-Examined. Behavioral and Brain Sciences 20 (1):83-83.
Added to index2009-01-28
Total downloads6 ( #154,584 of 722,700 )
Recent downloads (6 months)0
How can I increase my downloads?