Stability analysis of neural net controllers using fuzzy neural networks (Q1299627)

The authors consider the discrete feedback model \[ \begin{aligned} Y_{k +1} & = P(Y_k,u_k)\\ u_k & =C(e_k,\Delta e_k),\;e_k=Y_k-s,\;\Delta e_k=e_k-e_{k-1}\end{aligned} \] and the stabilizability problem, i.e., existence of \(C(\cdot, \cdot)\) such that \(|Y_k-s |< \varepsilon\) for \(k>k_0\). One studies the fuzzy neural network implementation of the feedback stabilizer \(C\) (here, a fuzzy neural network is a neural network that has fuzzy functions as weights).