The Origin of CBRAM With High Linearity, ON/OFF Ratio, and State Number for Neuromorphic Computing
Published in IEEE-TED(IEEE TRANSACTIONS ON ELECTRON DEVICES), 2021
The accuracy of the CBRAM array-based neural network is not high enough due to the low linearity, limited ON/OFF ratio, and the number of states. In this work, the origin of the characteristics of CBRAM has been revealed from the filament distribution of the devices, which inspires us to design an inserted graphene structure of CBRAM and preset seeds leading to high linearity (0.995), ON/OFF ratio (26.4), and the number of states (63). The Monte Carlo simulation results reveal that the CBRAM with more seeds can promote a larger number of potential advantage path (PAP) conducing better characteristics. Finally, a Multi-layer perceptron network has been realized by using a 1T-1R array, and achieved high recognition accuracy (92%) on the MNIST classification dataset, which shows that devices with higher PAP can eventually promote higher recognition accuracy.