Document Type



Unlike feedforward neural networks (FFNN) which can act as universal function approximators, recursive, or recurrent, neural networks can act as universal approximators for multi-valued functions. In this paper, a real time recursive backpropagation (RTRBP) algorithm in a vector matrix form is developed for a two-layer globally recursive neural network that has multiple delays in its feedback path. This algorithm has been evaluated on two GRNNs that approximate both an analytic and nonanalytic periodic multi-valued function that a feedforward neural network is not capable of approximating.


Back propagation (Artificial intelligence); Globally recurrent neural network (GRNN); Hysteresis; Multi-valued periodic functions; Neural networks (Computer science); Periodic functions; Real time recursive backpropagation (RTRBP); Recurrent neural network (RNN); System approximation


Electronic version of an article published as:

International Journal on Computational Intelligence and Application, vol. 8, no. 4, 2009 pp. 395 - 411, December 2009. DOI No: 10.1142/S1469026809002667

©World Scientific Publishing Company

UNLV article access

Search your library