Home > Research > Publications & Outputs > A constructivist neural network model of German...

Electronic data

  • Icann99

    Submitted manuscript, 335 KB, PDF-document

Links

Text available via DOI:

View graph of relations

A constructivist neural network model of German verb inflection in agrammatic aphasia

Research output: Contribution in Book/Report/ProceedingsConference contribution

Published
Close
Publication date1999
Host publicationNinth International Conference on Artificial Neural Networks (ICANN99)
Place of PublicationEdison
PublisherINST ELECTRICAL ENGINEERS INSPEC INC
Pages916-921
Number of pages6
ISBN (Print)0-85296-721-7
<mark>Original language</mark>English

Conference

Conference9th International Conference on Artificial Neural Networks (ICANN99)
CityEDINBURGH
Period7/09/9910/09/99

Conference

Conference9th International Conference on Artificial Neural Networks (ICANN99)
CityEDINBURGH
Period7/09/9910/09/99

Abstract

We present a constructivist neural network that closely models the performance of agrammatic aphasics on German participle inflection. The network constructs a modular architecture leading to a double dissociation between regular and irregular verbs, and lesioning the trained network accounts for data obtained from aphasic subjects [6]. We analyze the internal structure of the network with respect to the representation of regular and irregular verbs and argue that the constructivist neural network presents a more plausible account of verb inflection than a recently proposed dual-mechanism theory.