Modeling the Functional Features of a Memristive Crossbar Array in Neuromorphic Electronic Modules

A model and methodology for simulating memristive crossbar arrays are developed taking into account voltage drops on interconnections, the step of restructuring the conductivity levels of memristive elements, and the nonlinearity of their current–voltage (IV) characteristics. The results of testing an spiking neural network (SNN) in the inference mode are obtained in the problem of image recognition using the developed modeling technique taking into account the characteristics of experimentally manufactured memristor structures.