Article
Details
Citation
Phillips W, Hay IM & Smith L (1993) Lexicality and pronunciation in a simulated neural net. British Journal of Mathematical and Statistical Psychology, 46 (2), pp. 193-205. https://doi.org/10.1111/j.2044-8317.1993.tb01011.x
Abstract
Self-supervised compressive neural nets can perform nonlinear multilevel latent structure analysis. They therefore have promise for cognitive theory. We study their use in the Seidenberg & McClelland (1989) model of reading. Analysis shows that self-supervised compression in their model can make only a limited contribution to lexical decision, and simulation shows that it interferes with the associative mapping into phonology. Self-supervised compression is therefore put to no good use in their model. This does not weaken the arguments for self-supervised compression, however, and we suggest possible beneficial uses that merit further study.
Journal
British Journal of Mathematical and Statistical Psychology: Volume 46, Issue 2
Status | Published |
---|---|
Publication date | 30/11/1993 |
Publisher | Wiley-Blackwell for The British Psychological Society |
ISSN | 0007-1102 |
People (2)
Emeritus Professor, Psychology
Emeritus Professor, Computing Science