EUVIMEDEUVIMED entdecken
Crossref

Parallel Training Time-to-First-Spike Spiking Neural Networks

Kaiwei Che, Wei Fang, Peng Xue, Yifan Huang, Zhengyu Ma, Yonghong Tian

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (3) · 1712-1720

DOI: 10.1609/aaai.v40i3.37149 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Kaiwei Che und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Spiking Neural Networks (SNNs) offer a promising energy-efficient computing paradigm owing to their event-driven properties and biologically inspired dynamics. Among various encoding schemes, Time-to-First-Spike (TTFS) is particularly notable for its extreme sparsity, utilizing a single spike per neuron to maximize energy efficiency. However, two significant challenges persist: effectively leveraging TTFS sparsity to minimize training costs on Graphics Processing Units (GPUs), and bridging the performance gap between TTFS-based SNNs and their rate-based counterparts. To address these issues, we propose a parallel training algorithm for accelerated execution and a novel decoding strategy for enhanced performance. Specifically, we derive both forward and backward propagation equations for parallelized TTFS SNNs, enabling precise calculation of first-spike timings and gradients. Furthermore, we analyze the limitations of existing output decoders and introduce a membrane potential–based decoder, complemented by an incremental time-step training strategy, to improve accuracy. Our approach achieves state-of-the-art accuracy for TTFS SNNs on several benchmarks, including MNIST (99.51%), Fashion-MNIST (93.14%), CIFAR-10 (95.06%), and CIFAR-100 (74.07%).

Zitieren

APA

Che, K., Fang, W., Xue, P., Huang, Y., Ma, Z., & Tian, Y. (2026). Parallel Training Time-to-First-Spike Spiking Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 40(3), 1712-1720. https://doi.org/10.1609/aaai.v40i3.37149

Vancouver

Che K, Fang W, Xue P, Huang Y, Ma Z, Tian Y. Parallel Training Time-to-First-Spike Spiking Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(3):1712-1720. doi:10.1609/aaai.v40i3.37149

BibTeX
@article{Che2026,
  author = {Che, Kaiwei and Fang, Wei and Xue, Peng and Huang, Yifan and Ma, Zhengyu and Tian, Yonghong},
  title = {Parallel Training Time-to-First-Spike Spiking Neural Networks},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {3},
  pages = {1712--1720},
  doi = {10.1609/aaai.v40i3.37149}
}
Kostenlos starten →