Memristive neural network circuit with fault tolerance for character recognition

Abstract Memristor-based neural networks are one of the most promising approaches for hardware implementation of artificial neural networks. In this paper, a memristor-based neural network circuit based on 1M1R synaptic array structure is designed for character recognition function. Compared to other memristive synaptic arrays, the 1M1R structure can reduce the number of used memristors. However, the memristor may malfunction due to fabrication defects and the influence of external factors, resulting in a decrease in the accuracy of the circuit’s character recognition, and a suitable solution needs to be found to improve the stability and durability of the circuit. Therefore, in this paper, a fault-tolerant module with feedback adjustment capability is designed in the memristive neural network circuit, which can re-adjust the weights of the memristors through insitu training to solve the multiple faults in the memristive neural network, and the effect of the fault-tolerance is verified by character recognition. The experimental results show that the designed memristive neural network circuit can accurately realize character recognition, and the designed fault-tolerant circuit can well tolerate multiple faults, which ensures the stable operation of the circuit under fault conditions.