en
Proceedings chapter
Open access
English

The Impact of Labels on Visual Categorisation: a Neural Network Model

Published inProceedings of the 30th Annual Conference of the Cognitive Science Society, Editors Love, B.C.; McRae, K. & Sloutsky, V.M., p. 397-402
Presented at Washington DC, July 23-26, 2008
PublisherAustin, TX : Cognitive Science Society
Publication date2008
Abstract

We propose a computational model of the impact of labels on visual categorisation. The proposed model is based on selforganising maps. The model successfully reproduces the experiments demonstrating the impact of labelling on infant categorisation reported in Plunkett, Hu, and Cohen (2008). Two architectures are explored. Both mimic infant behaviour in both the familiarisation and testing phases of the procedure, using a training regime which involves only single presentations of each stimulus. The model reproduced these results in the absence of a explicit teaching signal and predicts that the observed behaviour in infants is due to a transient form of learning that might lead to the emergence of hierarchically organised categorical structure.

Keywords
  • Self-organising maps
  • Connectionist modeling
  • Categorisation
  • Lexical development
Affiliation Not a UNIGE publication
Citation (ISO format)
GLIOZZI, Valentina et al. The Impact of Labels on Visual Categorisation: a Neural Network Model. In: Proceedings of the 30th Annual Conference of the Cognitive Science Society. Washington DC. Austin, TX : Cognitive Science Society, 2008. p. 397–402.
Main files (1)
Proceedings chapter
accessLevelPublic
Identifiers
  • PID : unige:22696
483views
113downloads

Technical informations

Creation08/29/2012 3:57:00 PM
First validation08/29/2012 3:57:00 PM
Update time03/14/2023 5:39:56 PM
Status update03/14/2023 5:39:56 PM
Last indexation02/12/2024 8:24:39 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack