Book chapter
OA Policy
English

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

Published in

French, R.M. & Thomas, E. (Ed.), From Associations To Rules. Connectionist Models of Behavior and Cognition, p. 66-77

Publisher

Singapore : World Scientific Publ.

Collection

  • Progress in Neural Processing; 17

Publication date

2008

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.

UNIGE affiliation entities

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. French, R.M. & Thomas, E. (Ed.). Singapore : World Scientific Publ., 2008. p. 66–77. (Progress in Neural Processing) doi: 10.1142/9789812797322_0006

Main files (1)

Book chapter (Published version)

Identifiers

ISBN

978-981-279-731-5
643views
363downloads

Technical informations

Creation

29/08/2012 17:38:00

First validation

29/08/2012 17:38:00

Update

29/01/2026 08:39:13

Status update

29/01/2026 08:39:13

Last indexation

29/01/2026 08:39:14
All rights reserved by Archive ouverte UNIGE and the University of Geneva
OpenAIRE Indexed & Validated