Please use this identifier to cite or link to this item:
Type: Conference paper
Title: An MCMC-based method of comparing connectionist models in cognitive science
Author: Woojae, K.
Navarro, D.
Pitt, M.
Myung, J.
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
Publisher: MIT Press
Publisher Place: Canada
Issue Date: 2004
Series/Report no.: Advances in neural information processing systems ; 16
ISBN: 0262201526
ISSN: 1049-5258
Conference Name: Conference on Neural Information Processing Systems (2003 : Vancouver, Canada)
Statement of
Woojae Kim, Daniel J. Navarro, Mark A. Pitt, In Jae Myung
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.
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.