Please use this identifier to cite or link to this item: https://hdl.handle.net/2440/91084
Type: Conference paper
Title: The relevance of labels in semi-supervised learning depends on category structure
Author: Vong, W.K.
Perfors, A.
Navarro, D.J.
Citation: Program of the 36th Annual Meeting of the Cognitive Science Society, 2014, pp.1718-1723
Publisher: Cognitive Science Society
Issue Date: 2014
ISBN: 9780991196708
Conference Name: 36th Annual Meeting of the Cognitive Science Society (CogSci 2014) (23 Jul 2014 - 26 Jul 2014 : Quebec City, Canada)
Statement of
Responsibility: 
Wai Keen Vong, Amy Perfors, Daniel Navarro
Abstract: The study of semi-supervised category learning has shown mixed results on how people jointly use labeled and unlabeled information when learning categories. Here we investigate the possibility that people are sensitive to the value of both labeled and unlabeled items, and that this depends on the structure of the underlying categories. We use an unconstrained free-sorting categorization experiment with a mixture of both labeled and unlabeled stimuli. The results showed that when the distribution of stimuli involved distinct clusters, participants preferred to use the same strategies to sort the stimuli regardless of whether they were given any additional category label information. However, when the stimuli distribution was ambiguous, the sorting strategies people used were strongly influenced by the labeled information given. We capture performance in both cases with an extension to Anderson’s Rational Model that does not know the exact number of category labels in advance.
Keywords: Semi-supervised learning, unsupervised learning, categorization, Bayesian modeling
Rights: © The Authors
Grant ID: http://purl.org/au-research/grants/arc/DP0773794
http://purl.org/au-research/grants/arc/FT110100431
http://purl.org/au-research/grants/arc/DE120102378
Published version: https://mindmodeling.org/cogsci2014/papers/299/
Appears in Collections:Aurora harvest 7
Psychology publications

Files in This Item:
File Description SizeFormat 
hdl_91084.pdfPublished version127.26 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.