Universal approximation using dynamic recurrent neural networks: discrete-time version

Liang Jin, M.M. Gupta, P.N. Nikiforuk
Proceedings of ICNN'95 - International Conference on Neural Networks  
In this paper, the approximation capability of a class of discrete-time dynamic recurrent neural networks (DRNNs) is studied. Analytical results presented show that some of the states of such a DRNN described by a set of difference equations may be used to approximate uniformly a state space trajectory produced by either a discrete-time nonlinear system or a continuous function on a closed discrete-time interval.
doi:10.1109/icnn.1995.488134 dblp:conf/icnn/JinGN95 fatcat:jxmaa5fg6ngg7p5h3ihhr7kkeq