EUVIMEDEUVIMED entdecken
Crossref

Artificial to Spiking Neural Networks Conversion with Calibration in Scientific Machine Learning

Qian Zhang, Chenxi Wu, Adar Kahana, George Em Karniadakis, Youngeun Kim, Yuhang Li, Priyadarshini Panda

SIAM Journal on Scientific Computing · 30.06.2025 · 47 (3) · C559-C577

DOI: 10.1137/24m1643232 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SIAM Journal on Scientific Computing, online erschienen am 02.05.2025. Verfasst von Qian Zhang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: DARPA and SRC, National Science Foundation, U.S. Department of Energy.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We introduce a method to convert physics-informed neural networks (PINNs), commonly used in scientific machine learning, to spiking neural networks (SNNs), which are expected to have higher energy efficiency compared to traditional artificial neural networks (ANNs). We first extend the calibration technique of SNNs to arbitrary activation functions beyond ReLU, making it more versatile, and we prove a theorem that ensures the effectiveness of the calibration. We successfully convert PINNs to SNNs, enabling computational efficiency for diverse regression tasks in solving multiple differential equations, including the unsteady Navier–Stokes equations. We demonstrate great gains in terms of overall efficiency, including separable PINNs (SPINNs), which accelerate the training process. Overall, this is the first work of this kind and the proposed method achieves relatively good accuracy with low spike rates.

Förderung

  • DARPA and SRC
  • National Science Foundation
  • U.S. Department of Energy
  • ONR Vannevar Bush Faculty Fellowship

Zitieren

APA

Zhang, Q., Wu, C., Kahana, A., Karniadakis, G. E., Kim, Y., Li, Y., & Panda, P. (2025). Artificial to Spiking Neural Networks Conversion with Calibration in Scientific Machine Learning. SIAM Journal on Scientific Computing, 47(3), C559-C577. https://doi.org/10.1137/24m1643232

Vancouver

Zhang Q, Wu C, Kahana A, Karniadakis GE, Kim Y, Li Y, et al. Artificial to Spiking Neural Networks Conversion with Calibration in Scientific Machine Learning. SIAM Journal on Scientific Computing. 2025;47(3):C559-C577. doi:10.1137/24m1643232

BibTeX
@article{Zhang2025,
  author = {Zhang, Qian and Wu, Chenxi and Kahana, Adar and Karniadakis, George Em and Kim, Youngeun and Li, Yuhang and Panda, Priyadarshini},
  title = {Artificial to Spiking Neural Networks Conversion with Calibration in Scientific Machine Learning},
  journal = {SIAM Journal on Scientific Computing},
  year = {2025},
  volume = {47},
  number = {3},
  pages = {C559--C577},
  doi = {10.1137/24m1643232}
}
Kostenlos starten →