Pseudo-Spiking Neurons: A Noise-Based Training Framework for Heterogeneous-Latency Spiking Neural Networks
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (34) · 28555-28563
DOI: 10.1609/aaai.v40i34.40086 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yuxuan Zhang und 4 weiteren Autor:innen.
Abstract (Originalsprache)
Spiking Neural Networks (SNNs) promise significant energy efficiency by processing information via sparse, event-driven spikes. However, realizing this potential is hindered by the conventional use of a rigid, uniform timestep, T. This constraint imposes a challenging trade-off between accuracy and latency, while also incurring the prohibitive training costs of Backpropagation Through Time (BPTT). To overcome this limitation, we introduce the Pseudo-Spiking Neuron (PseudoSN), a novel training proxy that conceptualizes latency as an intrinsic, learnable parameter for each neuron. Building on the efficiency of rate-based methods, the PseudoSN models temporal dynamics in a single, BPTT-free pass. It employs a learnable probabilistic noise scheme to emulate the discretization effects of spike generation (e.g., clipping and quantization), making the neuron-specific timestep—and thus latency—directly optimizable via backpropagation. Integrated into a hardware-aware objective, our framework trains heterogeneous-latency SNNs that autonomously learn to optimize the trade-offs among accuracy, latency and energy, establishing a new state-of-the-art on major benchmarks.
Zitieren
APA
Zhang, Y., Sun, Y., Li, H., Deng, Y., & Yao, W. (2026). Pseudo-Spiking Neurons: A Noise-Based Training Framework for Heterogeneous-Latency Spiking Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 40(34), 28555-28563. https://doi.org/10.1609/aaai.v40i34.40086
Vancouver
Zhang Y, Sun Y, Li H, Deng Y, Yao W. Pseudo-Spiking Neurons: A Noise-Based Training Framework for Heterogeneous-Latency Spiking Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(34):28555-28563. doi:10.1609/aaai.v40i34.40086
BibTeX
@article{Zhang2026,
author = {Zhang, Yuxuan and Sun, Yuhang and Li, Hongjue and Deng, Yue and Yao, Wen},
title = {Pseudo-Spiking Neurons: A Noise-Based Training Framework for Heterogeneous-Latency Spiking Neural Networks},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {34},
pages = {28555--28563},
doi = {10.1609/aaai.v40i34.40086}
}
EUVIMED