An artificial synapse based on NbS2 nanosheets for neural network classification

Neuromorphic computing offers a promising solution to the energy inefficiencies inherent in conventional von Neumann architectures by emulating biological neural systems. This study introduces an artificial synapse based on NbS2 nanosheets, which exhibits stable long-term potentiation and long-term depression, supporting its integration into artificial neural networks (ANNs) and convolutional neural networks (CNNs). After 50 training epochs, the ANN achieved an accuracy of 97.65% on the Modified National Institute of Standards and Technology (MNIST) handwritten digit dataset. Meanwhile, the CNN reached an accuracy of 89.30% on the Fashion-MNIST clothing classification task. These findings highlight the potential of NbS2 nanosheet-based artificial synapses for efficient pattern recognition in future neuromorphic computing systems.