Spintronic leaky-integrate-fire spiking neurons with self-reset and winner-takes-all for neuromorphic computing

Di Wang, Ruifeng Tang, Huai Lin, Long Liu, Nuo Xu, Yan Sun, Xuefeng Zhao, Ziwei Wang, Dandan Wang, Zhihong Mai, Yongjian Zhou, Nan Gao, Cheng Song, Lijun Zhu, Tom Wu, Ming Liu and Guozhong Xing ()
Additional contact information
Di Wang: Chinese Academy of Sciences
Ruifeng Tang: Chinese Academy of Sciences
Huai Lin: Chinese Academy of Sciences
Long Liu: Chinese Academy of Sciences
Nuo Xu: University of California
Yan Sun: Chinese Academy of Sciences
Xuefeng Zhao: Chinese Academy of Sciences
Ziwei Wang: Chinese Academy of Sciences
Dandan Wang: Jiufengshan Laboratory
Zhihong Mai: Jiufengshan Laboratory
Yongjian Zhou: Tsinghua University
Nan Gao: University of Science and Technology of China
Cheng Song: Tsinghua University
Lijun Zhu: Chinese Academy of Sciences
Tom Wu: The Hong Kong Polytechnic University
Ming Liu: Chinese Academy of Sciences
Guozhong Xing: Chinese Academy of Sciences

Nature Communications, 2023, vol. 14, issue 1, 1-12

Abstract: Abstract Neuromorphic computing using nonvolatile memories is expected to tackle the memory wall and energy efficiency bottleneck in the von Neumann system and to mitigate the stagnation of Moore’s law. However, an ideal artificial neuron possessing bio-inspired behaviors as exemplified by the requisite leaky-integrate-fire and self-reset (LIFT) functionalities within a single device is still lacking. Here, we report a new type of spiking neuron with LIFT characteristics by manipulating the magnetic domain wall motion in a synthetic antiferromagnetic (SAF) heterostructure. We validate the mechanism of Joule heating modulated competition between the Ruderman–Kittel–Kasuya–Yosida interaction and the built-in field in the SAF device, enabling it with a firing rate up to 17 MHz and energy consumption of 486 fJ/spike. A spiking neuron circuit is implemented with a latency of 170 ps and power consumption of 90.99 μW. Moreover, the winner-takes-all is executed with a current ratio >104 between activated and inhibited neurons. We further establish a two-layer spiking neural network based on the developed spintronic LIFT neurons. The architecture achieves 88.5% accuracy on the handwritten digit database benchmark. Our studies corroborate the circuit compatibility of the spintronic neurons and their great potential in the field of intelligent devices and neuromorphic computing.

Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-023-36728-1 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:14:y:2023:i:1:d:10.1038_s41467-023-36728-1

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-023-36728-1

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().