Approximation of Recurrent Neural Networks to Nonlinear Time-Variant Discrete Systems
Li Xiao · Acta Scientiarum Naturalium Universitatis Sunyatseni · 2002
The method of recurrent neural networks approximation is used in nonlinear discrete_time systems. For nonlinear time_variant discrete systems, the more common case, this paper proves that their finite time trajectory can be approximated with the state vector of the output units of recurrent neural networks to any degree.