An artificial synapse based on NbS2 nanosheets for neural network classification
AIP Advances · 01.07.2026 · 16 (7)
DOI: 10.1063/5.0319583 ↗Kurz gefasst
Fachartikel in der Zeitschrift AIP Advances, online erschienen am 15.07.2026. Verfasst von Ying Li und 5 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Shandong Province.
Abstract (Originalsprache)
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.
Förderung
- Natural Science Foundation of Shandong Province
Zitieren
APA
Li, Y., Meng, H., Zhang, J., Xiao, X., Alam, M. K., & Guo, J. (2026). An artificial synapse based on NbS2 nanosheets for neural network classification. AIP Advances, 16(7). https://doi.org/10.1063/5.0319583
Vancouver
Li Y, Meng H, Zhang J, Xiao X, Alam MK, Guo J. An artificial synapse based on NbS2 nanosheets for neural network classification. AIP Advances. 2026;16(7). doi:10.1063/5.0319583
BibTeX
@article{Li2026,
author = {Li, Ying and Meng, Haowen and Zhang, Jing and Xiao, Xia and Alam, Mehran Khan and Guo, Jiajun},
title = {An artificial synapse based on NbS2 nanosheets for neural network classification},
journal = {AIP Advances},
year = {2026},
volume = {16},
number = {7},
doi = {10.1063/5.0319583}
}
EUVIMED