TWO-STEP METHOD FOR CONSTRUCTING COMPACT MODELS OF RERAM ELEMENTS

Mathematical models of memristors are usually specified as dynamic systems relative to the state parameter of the element characterizing conductivity. In this case, the dependence of the current (or resistance) on the state parameter and the voltage applied to the element can be quite complex. Existing models often do not fully reproduce experimental data. In this regard, the paper proposes a two-stage method consisting of using classical models at the first stage and neural networks to approximate the dependence of the current on the state parameter and voltage at the second stage.