STRUCTURAL-CHANGE AND DEVELOPMENT IN REAL AND ARTIFICIAL NEURAL NETWORKS

Two related but different fields are reviewed. Initially some basic fa cts about developing real brains are set out and then work on dynamic neural networks is described. A dynamic neural network is defined as a ny artificial neural network that automatically changes its structure through exposure to input stimuli. Various models are described and ev aluated and the functional correlates of both regressive and progressi ve structural changes are discussed. The paper concludes that, if futu re modelling work is to be set within a more neurally-plausible framew ork, then it would be fruitful to examine networks in which the connec tivity between extant units is progressively embellished. (C) 1998 Els evier Science Ltd. All rights reserved.