EUVIMEDEUVIMED entdecken
Crossref

Dynamic Convolutional Neural Networks Based on Adaptive 2D Memristors

Heemyoung Hong, Xi Chen, Woohyun Cho, Ho Yeon Yoo, Jaewhan Oh, Minseok Kim, Geunwoo Hwang, Yongsoo Yang, Linfeng Sun, Zhongrui Wang, Heejun Yang

Advanced Functional Materials · 2025-04 · 35 (17)

DOI: 10.1002/adfm.202422321 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Functional Materials, online erschienen am 23.12.2024. Verfasst von Heemyoung Hong und 10 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 37 Literaturangaben. Gefördert von: Samsung Science and Technology Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Convolutional Neural Networks (CNNs) are pivotal in modern digital computing, particularly for tasks like image classification, inspired by the receptive fields of the human brain. Nevertheless, CNNs implemented on conventional digital computers face significant limitations due to inflexible kernels that cannot adjust to dynamic inputs, and the von Neumann architecture, which leads to inefficient data transfer between memory and processing units. This research presents a hardware‐software co‐designed solution, a Dynamic Convolutional Neural Network (dCNN), empowered by three‐terminal adaptive two‐dimensional (2D) memristors. These memristors consist of a vertical heterostructure integrating silver, an atomically thin insulator (CrPS 4 ), and graphene as a semimetal. This configuration allows for the dynamic tuning of conductive filament properties, emulating the heterosynaptic plasticity observed in biological neural systems. The three‐terminal memristor design permits the dCNN to actively adjust kernel weights in its attention layer according to the input stimuli. The empirical tests demonstrate that image classification accuracy using our adaptive 2D memristor‐enhanced dVGG reaches up to 94% on the CIFAR‐10 dataset, which exceeds the performance of static VGG. Furthermore, the energy efficiency of our dVGG significantly outperforms that of GPUs, aligning more closely with the energy dynamics of the human brain in terms of both consumption and classification accuracy.

Förderung

  • Samsung Science and Technology Foundation

Zitieren

APA

Hong, H., Chen, X., Cho, W., Yoo, H. Y., Oh, J., Kim, M., Hwang, G., Yang, Y., Sun, L., Wang, Z., & Yang, H. (2025). Dynamic Convolutional Neural Networks Based on Adaptive 2D Memristors. Advanced Functional Materials, 35(17). https://doi.org/10.1002/adfm.202422321

Vancouver

Hong H, Chen X, Cho W, Yoo HY, Oh J, Kim M, et al. Dynamic Convolutional Neural Networks Based on Adaptive 2D Memristors. Advanced Functional Materials. 2025;35(17). doi:10.1002/adfm.202422321

BibTeX
@article{Hong2025,
  author = {Hong, Heemyoung and Chen, Xi and Cho, Woohyun and Yoo, Ho Yeon and Oh, Jaewhan and Kim, Minseok and Hwang, Geunwoo and Yang, Yongsoo and Sun, Linfeng and Wang, Zhongrui and Yang, Heejun},
  title = {Dynamic Convolutional Neural Networks Based on Adaptive 2D Memristors},
  journal = {Advanced Functional Materials},
  year = {2025},
  volume = {35},
  number = {17},
  doi = {10.1002/adfm.202422321}
}
Kostenlos starten →