Robust high-gain DNN observer for non- linear stochastic continuous time systems

A class of nonlinear stochastic processes satysfying a Lipschitz-type strip condition and supplied by a linear output equation, is considered. Robust asymptotic (high-gain) state estimation for nonlinear stochastic processes via di erential neural networks is discussed. A new type learning law for the weight dynamics is suggested. By a stochastic Lyapunov-like analysis (with Ito formula implementation), the stability conditions for the state estimation error as well as for the neural nertwork weights are established. The upper bound for this error is derived. The numerical example, dealing with module -type nonlinearities, illustrates the e ectiveness of the suggested approach.