Neural Networks and Child Language Development:

Neural networks provide a basis for studying child language development in that such networks emphasise learning. We report a simulation of some key aspects of child language development during infancy. We argue that in order to simulate the uniquely human language learning, it is important to use a ‘conglomerate’ neural network architecture that integrates the collective strengths of a variety of neural networks in some principled fashion to take into account the diverse nature of inputs to and outputs from a child learning language. We present such a ‘conglomerate’ neural network architecture ACCLAIM that integrates both supervised and unsupervised learning algorithms, to simulate the learning of concepts, words, conceptual and semantic relations and simple word-order rules, thus mimicking the production of child-like one-word and twoword language. The simulations carried out are ‘language informed’ as realistic child language data has been used for training the neural networks.