INCREMENTAL COMMUNICATION FOR MULTILAYER NEURAL NETWORKS - ERROR ANALYSIS

Artificial neural networks (ANN's) involve a large amount of internode communications, To reduce the communication cost as well as the time of learning process in ANN's, we earlier proposed an incremental inter node communication method, In the incremental communication method, in stead of communicating the full magnitude of the output value of a nod e, only the increment or decrement to its previous value is sent on a communication link, In this paper, the effects of the limited precisio n incremental communication method on the convergence behavior and per formance of multilayer neural networks are investigated. The nonlinear aspects of representing the incremental values with reduced (limited) precision for the commonly used error backpropagation training algori thm are analyzed, It is shown that the nonlinear effect of small pertu rbations in the input(s)/output of a node does not enforce instability , The analysis is supported by simulation studies of two problems, The simulation results demonstrate that the limited precision errors are bounded and do not seriously affect the convergence of multilayer neur al networks.