A Physics-Informed Recurrent Neural Network for RRAM Modeling

Extracting behavioural models of RRAM devices has been challenging due to their unique “memory” behaviours, for which well-established modeling frameworks and systematic parameter extraction processes have not been available. In this work, we propose a physics-informed recurrent neural network (PiRNN) methodology to generate behavioural models of RRAM devices from practical measurement/simulation data. The proposed framework can faithfully capture the evolution of internal state and its impacts on the output. A series of modifications informed by the RRAM device physics are proposed to enhance the modeling capabilities. Integration strategy with existing SPICE-type simulators is also developed. Numerical experiments with real RRAM devices data demonstrate the feasibility and advantages of the proposed methodology.