Westermann, G. (1997). A constructivist neural network learns the past tense of English verbs. In Proceedings of the GALA '97 Conference on Language Acquisition, pages 393--398, Edinburgh, UK. HCRC. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Constructivist Neural Network Models of Cognitive Development - Westermann (2000) Self-citation (Westermann) (Correct)
....derivation (4.18) However, there was no empirical advantage of that more complex unit movement over the one derived here. The simulations of English past tense acquisition and agrammatic aphasic inflection processing were performed both with the CNN algorithm (chapters 5 and 6) and the SGNG (Westermann, 1997, 1998; Westermann, Willshaw, and Penke, 1999) The CNN algorithm led to much shorter training times (approximately 25 of SGNG) with fewer units generated in the hidden layer (also about 25 of SGNG) The numerical values for the parameters used in the simulations with the CNN algorithm are given ....
.... the class information, undermining the claim that the constructivist model does not learn in a rule based way (Marcus, personal communication) Although similar experiments as those described here have also been performed with a phoneme input to phoneme output mapping and yielded similar results (Westermann, 1997), here an additional experiment was performed in which an extra layer was trained to produce the phonological form of the past tense based on the verb stem together with the learned past tense class. This additional layer can then be integrated with the phoneme to class network (fig. 5.7) 5.5. ....
[Article contains additional citation context not shown here]
Westermann, G. (1997). A constructivist neural network learns the past tense of English verbs. In Proceedings of the GALA '97 Conference on Language Acquisition, pages 393--398, Edinburgh, UK. HCRC.
Single Mechanism but not Single Route: Learning Verb.. - Westermann Self-citation (Westermann) (Correct)
....can be seen as two ends of a continuum, with mixed verbs and the blends produced by children representing intermediate cases. An implemented model that is based on this view is a constructivist, single mechanism neural network that accounts for the phenomena found in past tense acquisition (Westermann, 1997, 1998) and in impaired adult language processing (Westermann et al. 1999) This model starts with direct connections between the input and the output units, and during the learning process it constructs a hidden layer of receptive elds in response to the input data. The model takes into account ....
Westermann, G. (1997). A constructivist neural network learns the past tense of English verbs, Proceedings of the GALA '97 Conference on Language Acquisition, HCRC, Edinburgh, UK, pp. 393-398.
The Emergence of Structured Receptive Fields in a Constructive.. - Bering (1997) (Correct)
No context found.
Westermann, G. (in press). A constructivist neural network learns the past tense of english verbs. In Proceedings of GALA 1997 .
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC