en
Book chapter
Open access
English

Constraints on generalisation in a self-organising model of early word learning

Published inFrom Associations To Rules. Connectionist Models of Behavior and Cognition, Editors French, R.M. & Thomas, E., p. 66-77
PublisherSingapore : World Scientific Publ.
Collection
  • Progress in Neural Processing; 17
Publication date2008
Abstract

We investigate from a modelling perspective how lexical structure can be grounded in the underlying speech and visual categories that infants have already acquired. We demonstrate that the formation of well-structured categories is an important prerequisite for successful generalisation of cross-modal associations such that even after a single presentation of a word-object pair, the model is able to generalise to other members of the category. This ability to generalise a label to objects of like kinds, commonly referred to as the taxonomic assumption, is an emergent property of the model and provides an explanatory framework for understanding aspects of infant word learning. Furthermore, we investigate the impact of constraints imposed on the Hebbian associations in the cross-modal training phase and identify the conditions under which generalisation does not take place.

Affiliation Not a UNIGE publication
Citation (ISO format)
MAYOR, Julien, PLUNKETT, Kim. Constraints on generalisation in a self-organising model of early word learning. In: From Associations To Rules. Connectionist Models of Behavior and Cognition. Singapore : World Scientific Publ., 2008. p. 66–77. (Progress in Neural Processing)
Main files (1)
Book chapter
accessLevelPublic
Identifiers
  • PID : unige:22701
ISBN978-981-279-731-5
539views
235downloads

Technical informations

Creation08/29/2012 5:38:00 PM
First validation08/29/2012 5:38:00 PM
Update time03/14/2023 5:39:57 PM
Status update03/14/2023 5:39:57 PM
Last indexation02/12/2024 8:24:42 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack