An algorithm of memristor switching with high precision to a state with preset resistance has been developed based on the application of voltage pulses with smoothly increasing amplitude and the duration varying randomly within preset limits. It is shown that the proposed algorithm can be implemented in memristor structures based on (Co_40Fe_40B_20)_ x (LiNbO_3)_100– x nanocomposites with x ≈ 10 at. %. Optimum parameters are selected for the algorithm operation with a minimum number of iterations that allows the accuracy of resistance setting to be no worse than 0.5%. The obtained results can be used in the creation of neuromorphic systems.
Разработаны Verilog-A-модели тормозного и возбуждающего нейронов с бипрямоугольной и битреугольной формами импульсов (спайков) и мемристивными синаптическими весами. Показана возможность сходимости весов в численном моделировании обучения по Хеббу нейрона на основе локальных правил модификации весов. Предложена схема нейросинаптического ядра для аппаратной реализации формальных и спайковых нейронных сетей на их основе.
The paper presents Verilog-A models of excitatory and inhibitory neurons with birectangular and bitriangular shapes of spikes. Besides, it highlights the possibility of convergence of weights in the numerical simulation of a neuron Hebbian learning based on local weight updates rules, as well as offers schemes for the neurosynaptic core for the hardware implementation of formal and spike neural network algorithms.
В работе исследованы мемристоры на базе нанокомпозита (НК) (CoFeB) x(LiNbO3)1-x и построена на их основе импульсная нейроморфная сеть (ИНС) с четырьмя входными и одним выходным нейроном. Было показано, что в ИНС на основе НК мемристивных синапсов, помимо частотного, возможно и временное кодирование образов.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.