Training Elman and Jordan networks for system identification using genetic algorithms

Abstract

Two of the well-known recurrent neural networks are the Elman network and the Jordan network. Recently, modifications have been made to these networks to facilitate their applications in dynamic systems identification. Both the original and the modified networks have trainable feedforward connections. However, in order that they can be trained essentially as feedforward networks by means of the simple backpropagation algorithm, their feedback connections have to be kept constant. For the training to converge, it is important to select correct values for the feedback connections, but finding these values manually can be a lengthy trial-and-error process. This paper describes the use of genetic algorithms (GAs) to train the Elman and Jordan networks for dynamic systems identification. The GA is an efficient, guided, random search procedure which can simultaneously obtain the optimal weights of both the feedforward and feedback connections.