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 > Emergent modularity and U-shaped learning in a ...
View graph of relations

« Back

Emergent modularity and U-shaped learning in a constructivist neural network learning the English past tense

Research output: Contribution in Book/Report/ProceedingsConference contribution

Published

Publication date1998
Host publicationProceedings of the Twentieth Annual Conference of the Cognitive Science Society
EditorsMorton Ann Gernsbacher, Sharon J. Derry
Place of publicationMahwah, N.J.
PublisherLAWRENCE ERLBAUM ASSOC PUBL
Pages1130-1135
Number of pages6
ISBN (Print)0-8058-3231-9
Original languageEnglish

Conference

Conference20th Annual Conference of the Cognitive-Science-Society
CityMADISON
Period1/08/984/08/98

Conference

Conference20th Annual Conference of the Cognitive-Science-Society
CityMADISON
Period1/08/984/08/98

Abstract

A constructivist neural network model is presented that learns the past tense of English verbs. The model builds its architecture in response to the learning task in a way consistent with neurobiological and psychological evidence. The model outperforms existing connectionist and symbolic past tense models in terms of learning and generalization behavior, and it displays a U-shaped learning curve for many irregular verbs. The trained model develops a modular architecture with dissociations between regular and irregular verbs, and lesioning the different pathways leads to results comparable with neurological disorders. It is argued that the success of the model is due to its constructivist nature, and that the distinction between fixed-architecture and constructivist models is fundamental. Given this distinction, constructivist systems provide more realistic models of cognitive development.