Connectionist modelling of word recognition

Synthese 129 (2):173 - 183 (2001)
Connectionist models offer concretemechanisms for cognitive processes. When these modelsmimic the performance of human subjects theycan offer insights into the computationswhich might underlie human cognition. We illustratethis with the performance of a recurrentconnectionist network which produces the meaningof words in response to their spellingpattern. It mimics a paradoxical pattern oferrors produced by people trying to read degradedwords. The reason why the network produces thesurprising error pattern lies in the nature ofthe attractors which it develops as it learns tomap spelling patterns to semantics. The keyrole of attractor structure in the successfulsimulation suggests that the normal adult semanticreading route may involve attractor dynamics, andthus the paradoxical error pattern isexplained.
Keywords Philosophy   Philosophy   Epistemology   Logic   Metaphysics   Philosophy of Language
Categories (categorize this paper)
Reprint years 2004
DOI 10.1023/A:1013003423323
 Save to my reading list
Follow the author(s)
Edit this record
My bibliography
Export citation
Find it on Scholar
Mark as duplicate
Request removal from index
Revision history
Download options
Our Archive

Upload a copy of this paper     Check publisher's policy     Papers currently archived: 30,248
Through your library
References found in this work BETA

No references found.

Add more references

Citations of this work BETA

No citations found.

Add more citations

Similar books and articles
Added to PP index

Total downloads
19 ( #265,357 of 2,192,160 )

Recent downloads (6 months)
4 ( #59,667 of 2,192,160 )

How can I increase my downloads?

Monthly downloads
My notes
Sign in to use this feature