Efficient Spiking Neural Networks with Quantization-Aware Training for Edge Neuromorphic Deployment
Xiaojie Chen · Computer Science Bulletin · 2025
Not cached yet. This record was fetched live for this request and is stored after the lookup. Reopening the page should serve the cached copy.
Computer Science Bulletin · OpenAlex · article · 2025
Abstract
Spiking Neural Networks (SNNs) have emerged as a promising paradigm for energy-efficient machine learning, leveraging event-driven computation and sparse data processing to mimic biological neural mechanisms. However, deploying high-performance SNNs on resource-constrained edge neuromorphic hardware remains a significant challenge due to the high memory footprint and computational costs associated with full-precision weights and membrane potentials. While quantization is a well-established technique for Artificial Neural Networks (ANNs), its direct application to SNNs is complicated by the non-differentiable nature of spiking functions and the temporal dynamics of neuronal states.
This paper presents a comprehensive framework for Efficient Spiking Neural Networks via Quantization-Aware Training (QAT). We propose a novel differentiable quantization scheme that integrates learnable step-size parameters directly into the surrogate gradient learning loop, allowing the network to adapt its dynamic range during training. Furthermore, we introduce a bit-width adaptive Leaky Integrate-and-Fire (LIF) neuron model that mitigates the information loss typically observed in low-precision spiking regimes.
Our approach is validated on standard static and neuromorphic datasets, demonstrating that 4-bit quantized SNNs can achieve accuracy comparable to full-precision counterparts while reducing memory usage by 75% and energy consumption by over 60% on edge devices.
Open the resolved locator · 10.71465/csb169
Metadata licence: OpenAlex metadata (CC0)