ANALYZING A SELF-ORGANIZING ALGORITHM

A self-organising algorithm is described, which is a generalisation of an algorithm proposed by Cottrell and Fort. The algorithm is analysed in a more general fashion using the ordinary differential equation me thod (ODE) of stochastic approximation theory. The result is a set of linear equations which the stationary state of the neuron weights must satisfy. Several features of the algorithm are analysed including the conditions necessary for the existence of a single stationary point a s well as the configuration of the stationary state. It is shown what conditions favour the convergence of the neuron weights towards an org anised configuration. (C) 1997 Elsevier Science Ltd.