Home > Research > Publications & Outputs > Emergent modularity and U-shaped learning in a ...
View graph of relations

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

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Emergent modularity and U-shaped learning in a constructivist neural network learning the English past tense. / Westermann, G .
Proceedings of the Twentieth Annual Conference of the Cognitive Science Society. ed. / Morton Ann Gernsbacher; Sharon J. Derry. Mahwah, N.J.: LAWRENCE ERLBAUM ASSOC PUBL, 1998. p. 1130-1135.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Westermann, G 1998, Emergent modularity and U-shaped learning in a constructivist neural network learning the English past tense. in MA Gernsbacher & SJ Derry (eds), Proceedings of the Twentieth Annual Conference of the Cognitive Science Society. LAWRENCE ERLBAUM ASSOC PUBL, Mahwah, N.J., pp. 1130-1135, 20th Annual Conference of the Cognitive-Science-Society, MADISON, 1/08/98.

APA

Westermann, G. (1998). Emergent modularity and U-shaped learning in a constructivist neural network learning the English past tense. In M. A. Gernsbacher, & S. J. Derry (Eds.), Proceedings of the Twentieth Annual Conference of the Cognitive Science Society (pp. 1130-1135). LAWRENCE ERLBAUM ASSOC PUBL.

Vancouver

Westermann G. Emergent modularity and U-shaped learning in a constructivist neural network learning the English past tense. In Gernsbacher MA, Derry SJ, editors, Proceedings of the Twentieth Annual Conference of the Cognitive Science Society. Mahwah, N.J.: LAWRENCE ERLBAUM ASSOC PUBL. 1998. p. 1130-1135

Author

Westermann, G . / Emergent modularity and U-shaped learning in a constructivist neural network learning the English past tense. Proceedings of the Twentieth Annual Conference of the Cognitive Science Society. editor / Morton Ann Gernsbacher ; Sharon J. Derry. Mahwah, N.J. : LAWRENCE ERLBAUM ASSOC PUBL, 1998. pp. 1130-1135

Bibtex

@inproceedings{cbb4bf791ec347ed80e35ed86a4034b2,
title = "Emergent modularity and U-shaped learning in a constructivist neural network learning the English past tense",
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.",
keywords = "COGNITIVE-DEVELOPMENT, MODEL, LANGUAGE, SYSTEM",
author = "G Westermann",
year = "1998",
language = "English",
isbn = "0-8058-3231-9",
pages = "1130--1135",
editor = "Gernsbacher, {Morton Ann} and Derry, {Sharon J.}",
booktitle = "Proceedings of the Twentieth Annual Conference of the Cognitive Science Society",
publisher = "LAWRENCE ERLBAUM ASSOC PUBL",
note = "20th Annual Conference of the Cognitive-Science-Society ; Conference date: 01-08-1998 Through 04-08-1998",

}

RIS

TY - GEN

T1 - Emergent modularity and U-shaped learning in a constructivist neural network learning the English past tense

AU - Westermann, G

PY - 1998

Y1 - 1998

N2 - 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.

AB - 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.

KW - COGNITIVE-DEVELOPMENT

KW - MODEL

KW - LANGUAGE

KW - SYSTEM

M3 - Conference contribution/Paper

SN - 0-8058-3231-9

SP - 1130

EP - 1135

BT - Proceedings of the Twentieth Annual Conference of the Cognitive Science Society

A2 - Gernsbacher, Morton Ann

A2 - Derry, Sharon J.

PB - LAWRENCE ERLBAUM ASSOC PUBL

CY - Mahwah, N.J.

T2 - 20th Annual Conference of the Cognitive-Science-Society

Y2 - 1 August 1998 through 4 August 1998

ER -