Passive LiNbO₃ Memristor With Multilevel States for Neuromorphic Computing

The implementation of multilevel conductance states is still difficult for passive memristors used in neuromorphic computing. Here, a passive single-crystalline LiNbO₃ (LN) memristor with multilevel states was proposed, which can be precisely programmed into multilevel target states (with a standard deviation below $0.008~\mu $ s). Moreover, 32 separated and reliable conductance states can be achieved. The pattern recognition simulation for different numbers of conductance states ( ${N}_{\textrm {G}}$ ) is performed. As ${N}_{\textrm {G}}$ increases, the inference accuracy rises and reaches 98.01% when ${N}_{\textrm {G}}$ is 32. Even taking into account the conductance programming and drift error of the memristors, the accuracy can still reach 90.37%. The results validate the application potential of this passive memristor with 32 conductance states in neuromorphic computing.