EUVIMEDEUVIMED entdecken
Crossref

An Artificial L‐ReLU Neuron with Asymmetric Diffusive Memristor for High‐Accuracy Neuromorphic Systems

Jianxun Zou, Zhe Feng, Zhibin Qian, Zuheng Wu, Jingqi Zheng, Lubo Gao, Ruotong Yang, Wenbin Guo, Zhihao Lin, Yang Hao, Haochen Wang, Hao Ruan und 4 weitere

Advanced Functional Materials · 2025-05 · 35 (20)

DOI: 10.1002/adfm.202423267 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Functional Materials, online erschienen am 07.01.2025. Verfasst von Jianxun Zou und 15 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: Natural Science Foundation of Anhui Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Artificial neurons with leaky rectified linear unit (L‐ReLU) function can effectively process negative information, enhancing the neuromorphic systems capbility to handle negative values. Memristive devices show great potential in building compact and bio‐plausible artificial neurons, however, a neuron device that supports L‐ReLU functions is still lacking. In this work, a compact L‐ReLU neuron is proposed based on a bipolar asymmetrical diffusive memristor. Utilizing intercalation and leveraging the migration diffusion ratio of Ag ions, devices meeting the characteristics of the L‐ReLU function are fabricated (Ag/TaO x /SiO x /Pt). Thus, the constructed neuron can encode the positive and negative input information into positive and negative spikes, respectively, with L‐ReLU‐like response function. In addition, to address the problem that the frequency only has positive values, a vector frequency (VF) is defined to describe the frequency of the positive and negative spikes. Moreover, a convolutional neural network and You‐Only‐Look‐Once version 3 (YOLOv3) network are constructed with the L‐ReLU neurons for gesture language recognition and target detection tasks, respectively. The network based on L‐ReLU neurons can avoid negative information squandering, showing a higher inference accuracy than the network with ReLU neurons. The results show that the neurons can offer a promising platform for building high‐accuracy neuromorphic systems.

Förderung

  • Natural Science Foundation of Anhui Province

Zitieren

APA

Zou, J., Feng, Z., Qian, Z., Wu, Z., Zheng, J., Gao, L., Yang, R., Guo, W., Lin, Z., Hao, Y., Wang, H., Ruan, H., Xu, Z., Zhu, Y., Zhang, X., & Dai, Y. (2025). An Artificial L‐ReLU Neuron with Asymmetric Diffusive Memristor for High‐Accuracy Neuromorphic Systems. Advanced Functional Materials, 35(20). https://doi.org/10.1002/adfm.202423267

Vancouver

Zou J, Feng Z, Qian Z, Wu Z, Zheng J, Gao L, et al. An Artificial L‐ReLU Neuron with Asymmetric Diffusive Memristor for High‐Accuracy Neuromorphic Systems. Advanced Functional Materials. 2025;35(20). doi:10.1002/adfm.202423267

BibTeX
@article{Zou2025,
  author = {Zou, Jianxun and Feng, Zhe and Qian, Zhibin and Wu, Zuheng and Zheng, Jingqi and Gao, Lubo and Yang, Ruotong and Guo, Wenbin and Lin, Zhihao and Hao, Yang and Wang, Haochen and Ruan, Hao and Xu, Zuyu and Zhu, Yunlai and Zhang, Xumeng and Dai, Yuehua},
  title = {An Artificial L‐ReLU Neuron with Asymmetric Diffusive Memristor for High‐Accuracy Neuromorphic Systems},
  journal = {Advanced Functional Materials},
  year = {2025},
  volume = {35},
  number = {20},
  doi = {10.1002/adfm.202423267}
}
Kostenlos starten →