Can connectionist models of word pronunciation account for phonology?
Iris Berent Department of Psychology, Florida Atlantic University IBERENT@FAU.EDU In the past decade we have witnessed a heated controversy between eliminative connectionism and symbolic accounts of cognition. Despite dozens of connectionist models in diverse areas of cognition, the consequences of their architectural choices are not fully understood. How is a model s ability to generalize constrained by its architecture? Are different domains comparable in the class of generalizations they support? Does the ability of an architecture to generalize in a given domain guarantee generalization in a different domain? Marcus’s book (Marcus, in press) provides a lucid discussion of these issues and some formal tools for their evaluation. He demonstrates a systematic link between a model`s representational choices and the scope of the generalizations it can acquire: Eliminative connectionist networks can generalize only within the set of features on which they were trained, whereas networks i
