Spiking neural networks (SNNs) offer inherent energy efficiency due to their event-driven computation model, making them promising for edge AI deployment. However, their practical adoption is limited by the computational overhead of deep architectures and the absence of input-adaptive control. This work presents SPARQ, a unified framework that integrates spiking computation, quantization-aware training, and reinforcement learning-guided early exits for efficient and adaptive inference. Evaluations across MLP, LeNet, and AlexNet architectures demonstrated that the proposed Quantised Dynamic SNNs (QDSNN) consistently outperform conventional SNNs and QSNNs, achieving up to 5.15% higher accuracy over QSNNs, over 330 times lower system energy compared to baseline SNNs, and over 90 percent fewer synaptic operations across different datasets. These results validate SPARQ as a hardware-friendly, energy-efficient solution for real-time AI at the edge.

翻译：脉冲神经网络（SNNs）凭借其事件驱动的计算模型具有固有的能效优势，因此在边缘AI部署中前景广阔。然而，深度架构的计算开销以及缺乏输入自适应控制限制了其实际应用。本文提出了SPARQ，一个将脉冲计算、量化感知训练和强化学习引导的早期退出机制相统一的框架，以实现高效且自适应的推理。在MLP、LeNet和AlexNet架构上的评估表明，所提出的量化动态脉冲神经网络（QDSNN）持续优于传统SNN和量化SNN（QSNN）：相较于QSNN准确率最高提升5.15%，相比基线SNN系统能耗降低超过330倍，在不同数据集上突触操作减少超过90%。这些结果验证了SPARQ作为一种硬件友好、高能效的解决方案，适用于实时边缘AI。