EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An efficient full-size convolutional computing method based on memristor crossbar

Jinpei Tan, Siyuan Shen, Shukai Duan, Lidan Wang

Artificial Intelligence Review · 29.05.2024 · 57 (6)

DOI: 10.1007/s10462-024-10787-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Artificial Intelligence Review, online erschienen am 29.05.2024. Verfasst von Jinpei Tan und 3 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Chongqing, National Natural Science Foundation of China, Chongqing Talent Plan "Contract System" Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Modern artificial intelligence systems based on neural networks need to perform a large number of repeated parallel operations quickly. Without hardware acceleration, they cannot achieve effectiveness and availability. Memristor-based neuromorphic computing systems are one of the promising hardware acceleration strategies. In this paper, we propose a full-size convolution algorithm (FSCA) for the memristor crossbar, which can store both the input matrix and the convolution kernel and map the convolution kernel to the entire input matrix in a full parallel method during the computation. This method dramatically increases the convolutional kernel computations in a single operation, and the number of operations no longer increases with the input matrix size. Then a bidirectional pulse control switch integrated with two extra memristors into CMOS devices is designed to effectively suppress the leakage current problem in the row and column directions of the existing memristor crossbar. The spice circuit simulation system is built to verify that the design convolutional computation algorithm can extract the feature map of the entire input matrix after only a few operations in the memristor crossbar-based computational circuit. System-level simulations based on the MNIST classification task verify that the designed algorithm and circuit can effectively implement Gabor filtering, allowing the multilayer neural network to improve the classification task recognition accuracy to 98.25% with a 26.2% reduction in network parameters. In comparison, the network can even effectively immunize various non-idealities of the memristive synaptic within 30%.

Förderung

  • Natural Science Foundation of Chongqing
  • National Natural Science Foundation of China
  • Chongqing Talent Plan "Contract System" Project

Zitieren

APA

Tan, J., Shen, S., Duan, S., & Wang, L. (2024). An efficient full-size convolutional computing method based on memristor crossbar. Artificial Intelligence Review, 57(6). https://doi.org/10.1007/s10462-024-10787-2

Vancouver

Tan J, Shen S, Duan S, Wang L. An efficient full-size convolutional computing method based on memristor crossbar. Artificial Intelligence Review. 2024;57(6). doi:10.1007/s10462-024-10787-2

BibTeX
@article{Tan2024,
  author = {Tan, Jinpei and Shen, Siyuan and Duan, Shukai and Wang, Lidan},
  title = {An efficient full-size convolutional computing method based on memristor crossbar},
  journal = {Artificial Intelligence Review},
  year = {2024},
  volume = {57},
  number = {6},
  doi = {10.1007/s10462-024-10787-2}
}
Kostenlos starten →