Spiking Neural Networks (SNNs) provide an attractive framework for energy-efficient inference due to their event-driven computation and biologically inspired dynamics. However, efficient hardware realization of SNNs remains challenging because neuronal computations incur significant power and area costs, and uncontrolled approximate arithmetic can destabilize recurrent state updates when precision is not properly managed. To address these challenges, this paper presents ReSCom, a reconfigurable SNN accelerator that leverages stochastic computing to reduce hardware complexity while maintaining stable inference. The proposed architecture employs stochastic arithmetic for multiplication operations in neuron dynamics, while preserving exact fixed-point addition/subtraction operations. This stochastic strategy enables runtime trade-offs between accuracy, latency, and energy consumption. A unified reconfigurable neuron design supports Integrate-and-Fire (IF), Leaky Integrate-and-Fire (LIF), and Synaptic neuron models within a single hardware framework. Experimental results for MNIST inference on a Xilinx Artix-7 FPGA show that ReSCom achieves $92.80\%$ classification accuracy while consuming just $0.05~\mathrm{mJ}$ of operational energy per image at $100~\mathrm{MHz}$, outperforming the energy efficiency of recent state-of-the-art implementations. Furthermore, managing the stochastic bit-stream length allows explicit, dynamic control over accuracy-latency-energy trade-offs to meet target application constraints.

翻译：脉冲神经网络凭借其事件驱动计算和生物启发动力学特性，为高能效推理提供了富有吸引力的框架。然而，由于神经元计算会带来显著的功耗和面积开销，且当精度未妥善管理时，不受控的近似算术运算可能破坏循环状态更新的稳定性，因此脉冲神经网络的高效硬件实现仍面临挑战。针对这些问题，本文提出了ReSCom——一种利用随机计算降低硬件复杂度同时保持稳定推理的可重构脉冲神经网络加速器。该架构采用随机算术运算实现神经元动力学中的乘法操作，同时保留精确的定点加减法运算。这种随机策略支持在精度、延迟和能耗之间进行运行时权衡。统一的神经元可重构设计在单一硬件框架内支持积分点火、泄漏积分点火和突触神经元模型。在Xilinx Artix-7 FPGA上进行的MNIST推理实验结果表明，ReSCom在100 MHz工作频率下可达到92.80%的分类准确率，每幅图像仅消耗0.05毫焦耳运行能量，其能效优于近期最优实现方案。此外，管理随机比特流长度可实现对精度-延迟-能耗权衡的动态显式调控，以满足目标应用约束。