DocumentCode
1749073
Title
The prediction-irrelevance problem in grammar learning
Author
Spiegel, Rainer ; Jones, Fergal W. ; McLaren, IPL
Author_Institution
Dept. of Exp. Psychol., Cambridge Univ., UK
Volume
1
fYear
2001
fDate
2001
Firstpage
314
Abstract
The Elman recurrent network (SRN) has been considered a good model of language acquisition including grammar learning. Until recently, however, it was reported that it cannot master the prediction-irrelevance criterion, which, if true, would clearly limit its success of being an adequate neural network in this context. The paper shows that the SRN can deal with prediction-irrelevant information
Keywords
learning (artificial intelligence); psychology; recurrent neural nets; Elman recurrent network; grammar learning; language acquisition; prediction-irrelevance problem; simple recurrent network; Cognitive science; Humans; Intelligent networks; Learning systems; Neural networks; Pediatrics; Predictive models; Psychology; Statistical learning; Statistics;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on
Conference_Location
Washington, DC
ISSN
1098-7576
Print_ISBN
0-7803-7044-9
Type
conf
DOI
10.1109/IJCNN.2001.939038
Filename
939038
Link To Document