Application of Prony signal analysis to recurrent neural networks
Mohammad Farrokhi, C. Isik · 1994
Recurrent neural networks are highly nonlinear dynamic systems, and therefore it is not an easy task to analyze their dynamic behavior. The primary goal of this paper is to apply Prony signal analysis and a modified root locus technique to recurrent neural networks. The Prony method is compared with other linearization methods to analyze recurrent neural networks, and their performances are demonstrated using simulated examples.>