EUVIMEDEUVIMED entdecken
Open Access

SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence

Wei Fang iD, Yanqi Chen iD, Jianhao Ding iD, Zhaofei Yu iD, Timothée Masquelier iD, Ding Chen iD, Liwei Huang, Huihui Zhou iD, Guoqi Li iD, Yonghong Tian iD

Science Advances · 06.10.2023 · 9 (40)

DOI: 10.1126/sciadv.adi1480 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Advances, erschienen am 06.10.2023. Verfasst von Wei Fang und 9 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Peking University, China. Hauptthemen laut MEDLINE: Algorithms, Neurons. Die Arbeit wurde bisher 500-mal zitiert (Crossref) und nennt 194 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Spiking neural networks (SNNs) aim to realize brain-inspired intelligence on neuromorphic chips with high energy efficiency by introducing neural dynamics and spike properties. As the emerging spiking deep learning paradigm attracts increasing interest, traditional programming frameworks cannot meet the demands of the automatic differentiation, parallel computation acceleration, and high integration of processing neuromorphic datasets and deployment. In this work, we present the SpikingJelly framework to address the aforementioned dilemma. We contribute a full-stack toolkit for preprocessing neuromorphic datasets, building deep SNNs, optimizing their parameters, and deploying SNNs on neuromorphic chips. Compared to existing methods, the training of deep SNNs can be accelerated 11×, and the superior extensibility and flexibility of SpikingJelly enable users to accelerate custom models at low costs through multilevel inheritance and semiautomatic code generation. SpikingJelly paves the way for synthesizing truly energy-efficient SNN-based machine intelligence systems, which will enrich the ecology of neuromorphic computing.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsNeuronsNeural Networks, ComputerMachine LearningIntelligence

Autor:innen und Institutionen

  • School of Computer Science, Peking University, China.
  • Peng Cheng Laboratory, China.
  • School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University, China.
  • Institute for Artificial Intelligence, Peking University, China.
  • Centre de Recherche Cerveau et Cognition (CERCO), UMR5549 CNRS-Université Toulouse 3, France.
  • Department of Computer Science and Engineering, Shanghai Jiao Tong University, China.

ORCID-Profile: Wei Fang, Yanqi Chen, Jianhao Ding, Zhaofei Yu, Timothée Masquelier, Ding Chen, Huihui Zhou, Guoqi Li, Yonghong Tian

Zitieren

APA

Fang, W., Chen, Y., Ding, J., Yu, Z., Masquelier, T., Chen, D., Huang, L., Zhou, H., Li, G., & Tian, Y. (2023). SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence. Science Advances, 9(40). https://doi.org/10.1126/sciadv.adi1480

Vancouver

Fang W, Chen Y, Ding J, Yu Z, Masquelier T, Chen D, et al. SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence. Science Advances. 2023;9(40). doi:10.1126/sciadv.adi1480

BibTeX
@article{Fang2023,
  author = {Fang, Wei and Chen, Yanqi and Ding, Jianhao and Yu, Zhaofei and Masquelier, Timothée and Chen, Ding and Huang, Liwei and Zhou, Huihui and Li, Guoqi and Tian, Yonghong},
  title = {SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence},
  journal = {Science Advances},
  year = {2023},
  volume = {9},
  number = {40},
  doi = {10.1126/sciadv.adi1480}
}
Kostenlos starten →