Comparison of update and genetic training algorithms in a memristor crossbar perceptron

Memristor-based computer architectures are becoming more attractive as a possible choice of hardware for the implementation neural networks. However, at present, memristor technologies susceptible to variety failure modes, serious concern in any application where regular access may not be expected or even possible. In this study, we investigate whether certain training algorithms resilient particular modes and, therefore, suitable use those applications. We implement two algorithms—a local update scheme and genetic algorithm—in simulated crossbar compare their ability train simple image classification task an increasing number memristors fail adjust conductance. demonstrate that there is clear distinction between several measures rate train.