EUVIMEDExplore EUVIMED
Crossref

Efficient Spiking Neural Networks with Biologically Similar Lithium-Ion Memristor Neurons

Shanwu Ke, Yanqin Pan, Yaoyao Jin, Jiahao Meng, Yongyue Xiao, Siqi Chen, Zihao Zhang, Ruiqi Li, Fangjiu Tong, Bei Jiang, Zhitang Song, Min Zhu iD and 1 more

ACS Applied Materials & Interfaces · 2024-03-20 · 16 (11) · 13989-13996

DOI: 10.1021/acsami.3c19261 ↗

At a glance

Journal article in ACS Applied Materials & Interfaces, published online on 2024-03-05. Written by Shanwu Ke and 12 co-authors. Institution: School of Microelectronics, Key Laboratory of Intelligent Sensing System and Security, Ministry of Education, Hubei University, Wuhan 430062, China. Major MEDLINE topics: Lithium, Neural Networks, Computer. Cited 24 times so far (Crossref); 50 references. Funded by: National Natural Science Foundation of China, Wuhan Key Research and Development Program, Strategic Priority Research Program of Chinese Academy of Sciences.

AbstractSubjectsBibliographic detailsCiteRelated studies

Abstract (original language)

Benefiting from the brain-inspired event-driven feature and asynchronous sparse coding approach, spiking neural networks (SNNs) are becoming a potentially energy-efficient replacement for conventional artificial neural networks. However, neuromorphic devices used to construct SNNs persistently result in considerable energy consumption owing to the absence of sufficient biological parallels. Drawing inspiration from the transport nature of Na+ and K+ in synapses, here, a Li-based memristor (LixAlOy) was proposed to emulate the biological synapse, leveraging the similarity of Li as a homologous main group element to Na and K. The Li-based memristor exhibits ∼8 ns ultrafast operating speed, 1.91 and 0.72 linearity conductance modulation, and reproducible switching behavior, enabled by lithium vacancies forming a conductive filament mechanism. Moreover, these memristors are capable of simulating fundamental behaviors of a biological synapse, including long-term potentiation and long-term depression behaviors. Most importantly, a threshold-tunable leaky integrate-and-fire (TT-LIF) neuron is built using LixAlOy memristors, successfully integrating synaptic signals from both temporal and spatial levels and achieving an optimal threshold of SNNs. A computationally efficient TT-LIF-based SNN algorithm is also implemented for image recognition schemes, featuring a high recognition rate of 90.1% and an ultralow firing rate of 0.335%, which is 4 times lower than those of other memristor-based SNNs. Our studies reveal the ion dynamics mechanism of the LixAlOy memristor and confirm its potential in rapid switching and the construction of SNNs.

Subjects

MeSH terms (MEDLINE)

LithiumNeural Networks, ComputerAlgorithmsBrainIonsNeurons

Author keywords

artificial neuronelectronic synapselithium-dopedmemristorspiking neural network

Substances

LithiumIons

Authors and institutions

  • School of Microelectronics, Key Laboratory of Intelligent Sensing System and Security, Ministry of Education, Hubei University, Wuhan 430062, China.
  • Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai 200050, China.

ORCID profiles: Min Zhu, Cong Ye

Funding

  • National Natural Science Foundation of China
  • Wuhan Key Research and Development Program
  • Strategic Priority Research Program of Chinese Academy of Sciences
  • Key Research and Development Program of Hubei Province

Cite

APA

Ke, S., Pan, Y., Jin, Y., Meng, J., Xiao, Y., Chen, S., Zhang, Z., Li, R., Tong, F., Jiang, B., Song, Z., Zhu, M., & Ye, C. (2024). Efficient Spiking Neural Networks with Biologically Similar Lithium-Ion Memristor Neurons. ACS Applied Materials & Interfaces, 16(11), 13989-13996. https://doi.org/10.1021/acsami.3c19261

Vancouver

Ke S, Pan Y, Jin Y, Meng J, Xiao Y, Chen S, et al. Efficient Spiking Neural Networks with Biologically Similar Lithium-Ion Memristor Neurons. ACS Applied Materials & Interfaces. 2024;16(11):13989-13996. doi:10.1021/acsami.3c19261

BibTeX
@article{Ke2024,
  author = {Ke, Shanwu and Pan, Yanqin and Jin, Yaoyao and Meng, Jiahao and Xiao, Yongyue and Chen, Siqi and Zhang, Zihao and Li, Ruiqi and Tong, Fangjiu and Jiang, Bei and Song, Zhitang and Zhu, Min and Ye, Cong},
  title = {Efficient Spiking Neural Networks with Biologically Similar Lithium-Ion Memristor Neurons},
  journal = {ACS Applied Materials & Interfaces},
  year = {2024},
  volume = {16},
  number = {11},
  pages = {13989--13996},
  doi = {10.1021/acsami.3c19261}
}
Start for free →