EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Reconfigurable Memristive Spiking Neuron Enabling Advanced Neuromorphic Computing

Pek Jun Tiw iD, Yuqi Li, Zhongyuan Li, Qihang Ding, Yuzhe Wang, Jiarong Wang, Yuchao Yang iD

Advanced Science · 2026-11 · 13 (63)

DOI: 10.1002/advs.77375 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Science, online erschienen am 24.08.2026. Verfasst von Pek Jun Tiw und 6 weiteren Autor:innen. Beteiligte Einrichtung: New Cornerstone Science Laboratory, Beijing Advanced Innovation Center for Integrated Circuits, School of Integrated Circuits, Peking University, Bei…. Hauptthemen laut MEDLINE: Neurons, Neural Networks, Computer, Action Potentials. Die Arbeit nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China, Guangdong Provincial Key Laboratory of in-Memory Computing Chips, Shenzhen Science and Technology Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Biological neurons exhibit internal complexity that enables a variety of spiking behaviors, complex encoding strategies, and the possibility of advanced networks that underpin cognitive brain functions. Neuromorphic computing, especially using memristors with biologically plausible dynamics, is imperative to realizing next‐generation artificial intelligence. However, current attempts still rely on simple neurons with limited support for novel network algorithms. This work proposes a multi‐mode reconfigurable memristive spiking neuron with a simple transistor‐capacitor feedback circuit that enables fast‐spiking, adaptive spiking, phasic bursting, or single‐spiking. Every spike train parameter in each mode can be freely tuned. With this, a multiplexed encoding strategy in a hazard avoidance application is demonstrated, wherein 3 driving actions and 6 maneuvering control variables are encoded using distinct spiking modes and spike train parameters. Furthermore, long‐short‐term memory spiking neural networks (LSNN) that incorporate either heterogeneous slow time constants or dynamic mode switching are proposed, demonstrating up to 8.0% and 13.7% improvements in accuracy in highly temporal tasks compared with homogeneous LSNNs, while also exhibiting superior generalization capabilities. The ability to support these advanced encoding and network strategies distinguishes the proposed reconfigurable neuron from existing implementations, highlighting its potential to empower more advanced neuromorphic computing.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

NeuronsNeural Networks, ComputerAction PotentialsSoft ComputingAlgorithmsModels, NeurologicalHumansLong Short Term MemoryArtificial Intelligence

Stichwörter der Autor:innen

adaptationburstingfast‐spikingneural codingreconfigurablesingle‐spikingtunability

Autor:innen und Institutionen

  • New Cornerstone Science Laboratory, Beijing Advanced Innovation Center for Integrated Circuits, School of Integrated Circuits, Peking University, Beijing, China.
  • New Cornerstone Science Laboratory, Guangdong Provincial Key Laboratory of In-Memory Computing Chips, School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University, Shenzhen, China.
  • Center for Brain Inspired Chips, Institute For Artificial Intelligence, Peking University, Beijing, China.
  • Center for Brain Inspired Intelligence, Chinese Institute For Brain Research (CIBR), Beijing, China.

ORCID-Profile: Pek Jun Tiw, Yuchao Yang

Förderung

  • National Key R&D Program of China
  • Guangdong Provincial Key Laboratory of in-Memory Computing Chips
  • Shenzhen Science and Technology Program
  • Beijing Natural Science Foundation
  • National Natural Science Foundation of China
  • Financial Support for Outstanding Scientific and Technological Innovation Talents Training Fund in Shenzhen
  • New Cornerstone Science Foundation
  • Natural Science Foundation of Beijing Municipality

Zitieren

APA

Tiw, P. J., Li, Y., Li, Z., Ding, Q., Wang, Y., Wang, J., & Yang, Y. (2026). A Reconfigurable Memristive Spiking Neuron Enabling Advanced Neuromorphic Computing. Advanced Science, 13(63). https://doi.org/10.1002/advs.77375

Vancouver

Tiw PJ, Li Y, Li Z, Ding Q, Wang Y, Wang J, et al. A Reconfigurable Memristive Spiking Neuron Enabling Advanced Neuromorphic Computing. Advanced Science. 2026;13(63). doi:10.1002/advs.77375

BibTeX
@article{Tiw2026,
  author = {Tiw, Pek Jun and Li, Yuqi and Li, Zhongyuan and Ding, Qihang and Wang, Yuzhe and Wang, Jiarong and Yang, Yuchao},
  title = {A Reconfigurable Memristive Spiking Neuron Enabling Advanced Neuromorphic Computing},
  journal = {Advanced Science},
  year = {2026},
  volume = {13},
  number = {63},
  doi = {10.1002/advs.77375}
}
Kostenlos starten →