Stabilizing Spiking Neurons Through Biologically Inspired Polarization
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (27) · 22734-22741
DOI: 10.1609/aaai.v40i27.39435 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Matthew Lai und 1 weiteren Autor:innen.
Abstract (Originalsprache)
The Leaky Integrate-and-Fire (LIF) neuron model remains a staple in spiking neural networks (SNNs), yet its oversimplified dynamics lead to unstable gradients and limit scalability. We introduce a polarization-aware spiking architecture (POLARA) that models depolarization, repolarization, and hyperpolarization through analytically defined membrane dynamics. POLARA unifies biologically grounded design with stable gradient propagation—formulating both forward and backward paths directly, and applying gradient shaping solely for numerical control, without requiring learnable gates or surrogate tuning. By bounding membrane potentials within realistic voltage ranges, POLARA avoids vanishing and exploding gradients, enabling scalable training in deeper architectures. Experiments show consistent gains over LIF and competitive results against optimized SNNs, positioning POLARA as a principled alternative to surrogate-driven or reset-based designs.
Zitieren
APA
Lai, M., & Cao, L. (2026). Stabilizing Spiking Neurons Through Biologically Inspired Polarization. Proceedings of the AAAI Conference on Artificial Intelligence, 40(27), 22734-22741. https://doi.org/10.1609/aaai.v40i27.39435
Vancouver
Lai M, Cao L. Stabilizing Spiking Neurons Through Biologically Inspired Polarization. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(27):22734-22741. doi:10.1609/aaai.v40i27.39435
BibTeX
@article{Lai2026,
author = {Lai, Matthew and Cao, Longbing},
title = {Stabilizing Spiking Neurons Through Biologically Inspired Polarization},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {27},
pages = {22734--22741},
doi = {10.1609/aaai.v40i27.39435}
}
EUVIMED