Parallel Implementation of Memory Neuron Network for Identification of Dynamical System

This paper discusses parallel algorithm of memory neuron networks for identification of nonlinear dynamical systems. These are a class of recurrent networks obtained by adding trainable temporal elements to feed-forward networks that makes the output history-sensitive. By virtue of this capability, these networks can identify nonlinear dynamical systems without having to be explicitly fed past inputs and outputs. Artificial neural networks (ANN) consist of enormous number of massively interconnected nonlinear computational elements (neuron) and they are inherently parallel in nature. This paper presents an analysis of neuron parallelism or vertical slicing using Message Passing Interface (MPI) library routines. The results show that the parallel efficiency increase with increase in network size and also we can get linear speed up if the number of processors are increased.