Describes a connectionist model accounting for newborn infants' ability to finely discriminate almost all human speech contrasts and the fact that their phonemic category boundaries are identical, even for phonemes outside their target language. The model posits an innately guided learning in which an artificial neural network is stored in a…

Developmental aspects of spelling-to-sound mapping for English monosyllabic words are investigated with a simple two-layer network model using a simple, general learning rule. The model is trained on both regularly and irregularly spelled words but extracts regular spelling to sound relationships, which it can apply to new words. Training-related…

Proposes that an important role for connectionist research in language acquisition is analyzing what linguistic information is present in the child's input. Recent connectionist and statistical work analyzing the properties of real language corpora suggest a priori objections against the utility of distributional information are misguided. This…