Exemplar-based learning requires (i) a segmentation procedure for identifying the units of past experiences that a present experience can be compared to, and (ii) a similarity function for comparing these past experiences to the present experience. This article argues that for a learner to learn a language these two mechanisms will require abstractions such as linguistic features. Moreover, because the segmentation procedure will vary depending on the language, a radical exemplar theory is likely to require linguistic abstractions for learning.
AmbridgeB. (2020). Against stored abstractions: A radical exemplar model of language acquisition. First Language 40(5-6): 509–559.
2.
JäkelF.SchölkopfB.WinchmannF. A. (2008). Generalization and similarity in exemplar models of categorization: Insights from machine learning. Psychonomic Bulletin & Review, 15, 256–271.
3.
JamesW. (1950). The principles of psychology. Dover Publications. (Original work published 1890).
