Lancaster EPrints

Modelling cognitive development with constructivist neural networks

Westermann, G (2000) Modelling cognitive development with constructivist neural networks. In: Connectionist models of learning, development and evolution. Springer Verlag London Ltd, Godalming, pp. 123-132. ISBN 1-85233-354-5

Full text not available from this repository.


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.

Item Type: Contribution in Book/Report/Proceedings
Subjects: B Philosophy. Psychology. Religion > BF Psychology
Departments: Faculty of Science and Technology > Psychology
ID Code: 53367
Deposited By: ep_importer_pure
Deposited On: 27 Mar 2012 11:41
Refereed?: No
Published?: Published
Last Modified: 24 Mar 2018 00:04
Identification Number:

Actions (login required)

View Item