Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/40430
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Woojae, K. | - |
dc.contributor.author | Navarro, D. | - |
dc.contributor.author | Pitt, M. | - |
dc.contributor.author | Myung, J. | - |
dc.date.issued | 2004 | - |
dc.identifier.citation | Advances in neural information processing systems 16: proceedings of the 2003 conference / Sebastian Thrun, Lawrence K. Saul, and Bernhard Schölkopf (eds.): pp.937-944 | - |
dc.identifier.isbn | 0262201526 | - |
dc.identifier.isbn | 9780262201520 | - |
dc.identifier.issn | 1049-5258 | - |
dc.identifier.uri | http://hdl.handle.net/2440/40430 | - |
dc.description.abstract | Despite the popularity of connectionist models in cognitive science, their performance can often be difficult to evaluate. Inspired by the geometric approach to statistical model selection, we introduce a conceptually similar method to examine the global behavior of a connectionist model, by counting the number and types of response patterns it can simulate. The Markov Chain Monte Carlo-based algorithm that we constructed nds these patterns efficiently. We demonstrate the approach using two localist network models of speech perception. | - |
dc.description.statementofresponsibility | Woojae Kim, Daniel J. Navarro, Mark A. Pitt, In Jae Myung | - |
dc.language.iso | en | - |
dc.publisher | MIT Press | - |
dc.relation.ispartofseries | Advances in neural information processing systems ; 16 | - |
dc.title | An MCMC-based method of comparing connectionist models in cognitive science | - |
dc.type | Conference paper | - |
dc.contributor.conference | Conference on Neural Information Processing Systems (2003 : Vancouver, Canada) | - |
dc.publisher.place | Canada | - |
pubs.publication-status | Published | - |
dc.identifier.orcid | Navarro, D. [0000-0001-7648-6578] | - |
Appears in Collections: | Aurora harvest 6 Psychology publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.