12,000

We have over 12,000 students, from over 100 countries, within one of the safest campuses in the UK

93%

93% of Lancaster students go into work or further study within six months of graduating

Home > Research > Publications & Outputs > Modelling cognitive development with constructi...
View graph of relations

« Back

Modelling cognitive development with constructivist neural networks

Research output: Contribution in Book/Report/ProceedingsConference contribution

Published

Publication date2000
Host publicationConnectionist models of learning, development and evolution
EditorsRobert M. French, Jacques P. Sougne
Place of publicationGodalming
PublisherSpringer Verlag London Ltd
Pages123-132
Number of pages10
ISBN (Print)1-85233-354-5
Original languageEnglish

Conference

Conference6th Neural Computation and Psychology Workshop
CityLIEGE
Period16/09/0018/09/00

Conference

Conference6th Neural Computation and Psychology Workshop
CityLIEGE
Period16/09/0018/09/00

Abstract

Based on recent evidence from cognitive developmental neuroscience, I argue for the importance of constructivist models of cognitive developmental phenomena. This point is empirically investigated with a constructivist neural network model of the acquisition of past tense/participle inflections. The model dynamically adapts its architecture to the learning task by growing units and connections in a task-specific way during learning. In contrast to other, fixed-architecture models, the constructivist network displays a realistic, U-shaped learning behaviour. In the trained network, realistic "adult" representations emerge that lead to aphasia-like dissociations between regular and irregular forms when the model is lesioned. These results show that constructivist neural networks form valid models of cognitive developmental processes and that they avoid many of the problems of fixed-architecture models.