Accomplishing multi-level programming in resistive random access memory (RRAM) arrays with truly discrete and linearly spaced conductive levels is crucial in order to implement synaptic weights in hardware-based neuromorphic systems. In this paper, we implemented this feature on 4-kbit 1T1R RRAM arrays by tuning the programming parameters of the multi-level incremental step pulse with verify algorithm (M-ISPVA). The optimized set of parameters was assessed by comparing its results with a non-optimized one. The optimized set of parameters proved to be an effective way to define non-overlapped conductive levels due to the strong reduction of the device-to-device variability as well as of the cycle-to-cycle variability, assessed by inter-levels switching tests and during 1 k reset-set cycles. In order to evaluate this improvement in real scenarios, the experimental characteristics of the RRAM devices were captured by means of a behavioral model, which was used to simulate two different neuromorphic systems: an 8 × 8 vector-matrix-multiplication (VMM) accelerator and a 4-layer feedforward neural network for MNIST database recognition. The results clearly showed that the optimization of the programming parameters improved both the precision of VMM results as well as the recognition accuracy of the neural network in about 6% compared with the use of non-optimized parameters.
In this work, we present a model for describing the thermal noise performance of a general linear time invariant (LTI) passive 1-port by means of two partially correlated noise sources. The inclusion of an additional source compared to the conventional 1-source noise representation of 1-ports, allows for a more complete description of the thermal noise description not only at the external terminals of the considered admittance, but also in terms of the internal noise through its real part, guaranteeing the independence of the latter from the external circuit connected to it when thermodynamic equilibrium is considered. The results of the model demonstrate that the proposed noise modeling for linear 1-ports features an additional degree of freedom in the form of the level of correlation between both sources. We propose that this finding might be of application for maintaining a linear circuit modeling of the noise generated by a resistor with a small nonlinear resistive behavior by transferring this nonlinearity to the correlation between the sources.