Hybrid-SNN: CMOS 8T SRAM-Based Spiking Neural Network (SNN) Accelerator With Hybrid Leaky-and-Integrate Fire (LIF) Neuron for Optimized Energy Efficiency and Error Tolerance
IEEE Access · 2026 · 14 · 115313-115325
DOI: 10.1109/access.2026.3709837 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Honggu Kim und 3 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Chung-Ang University Graduate Research Scholarship, in 2024; in part by the National Research Council of Science and Technology through Korean Government [Mini…, Korea Institute of Science and Technology Institutional Program.
Abstract (Originalsprache)
Spiking Neural Networks (SNNs) are emerging as a promising paradigm in artificial intelligence, effectively mimicking the dynamic behavior of biological neural systems. SNN models typically employ Deterministic Leaky Integrate-and-Fire (D-LIF) or Stochastic Leaky Integrate-and-Fire (S-LIF) neurons, each optimized for specific performance goals. D-LIF neurons maximize energy efficiency through spike sparsity, while S-LIF neurons improve error tolerance. However, existing hardware lacks the capability to support both neuron types simultaneously. In this paper, we demonstrated Hybrid-SNN: CMOS implemented SNN accelerator with Hybrid LIF (H-LIF) neuron which is capable of operating as either D-LIF neuron or S-LIF neuron in a single hardware platform, enabling flexible deployment of various Hybrid-SNN configurations. Software-level simulations show that strategically distributing D-LIF and S-LIF neurons across specific layers enables the Hybrid-SNN to leverage the strengths of both neuron types: D-LIF neurons improve energy efficiency, while S-LIF neurons enhance error tolerance. This Hybrid configuration enhances both energy efficiency and computational robustness, outperforming single-mode neuron configurations. Fabricated using CMOS 180nm process technology, the Hybrid-SNN achieves an energy consumption of 1.62 pJ/SOP, offering a $1.59\times $ improvement over its Stochastic counterpart, and exhibits a low accuracy drop of 7.67% under a 5% random weight deviation scenario, achieving a $1.64\times $ improvement over its Deterministic counterpart.
Förderung
- Chung-Ang University Graduate Research Scholarship, in 2024; in part by the National Research Council of Science and Technology through Korean Government [Mini…
- Korea Institute of Science and Technology Institutional Program
Zitieren
APA
Kim, H., An, Y., Kim, J., & Shim, Y. (2026). Hybrid-SNN: CMOS 8T SRAM-Based Spiking Neural Network (SNN) Accelerator With Hybrid Leaky-and-Integrate Fire (LIF) Neuron for Optimized Energy Efficiency and Error Tolerance. IEEE Access, 14, 115313-115325. https://doi.org/10.1109/access.2026.3709837
Vancouver
Kim H, An Y, Kim J, Shim Y. Hybrid-SNN: CMOS 8T SRAM-Based Spiking Neural Network (SNN) Accelerator With Hybrid Leaky-and-Integrate Fire (LIF) Neuron for Optimized Energy Efficiency and Error Tolerance. IEEE Access. 2026;14:115313-115325. doi:10.1109/access.2026.3709837
BibTeX
@article{Kim2026,
author = {Kim, Honggu and An, Yerim and Kim, Jaeyoun and Shim, Yong},
title = {Hybrid-SNN: CMOS 8T SRAM-Based Spiking Neural Network (SNN) Accelerator With Hybrid Leaky-and-Integrate Fire (LIF) Neuron for Optimized Energy Efficiency and Error Tolerance},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {115313--115325},
doi = {10.1109/access.2026.3709837}
}
EUVIMED