In Spiking Neural Networks (SNNs), learning rules are based on neuron spiking behavior, that is, if and when spikes are generated due to a neuron's membrane potential exceeding that neuron's firing threshold, and this spike timing encodes vital information. However, the threshold is generally treated as a hyperparameter, and incorrect selection can lead to neurons that do not spike for large portions of the training process, hindering the effective rate of learning. Inspired by homeostatic mechanisms in biological neurons, this work (Rouser) presents a study to rouse training-inactive neurons and improve the SNN training by using an in-loop adaptive threshold learning mechanism. Rouser's adaptive threshold allows for dynamic adjustments based on input data and network hyperparameters, influencing spike timing and improving training. This study focuses primarily on investigating the significance of learning neuron thresholds alongside weights in SNNs. We evaluate the performance of Rouser on the spatiotemporal datasets NMNIST, DVS128 and Spiking Heidelberg Digits (SHD), compare our results with state-of-the-art SNN training techniques, and discuss the strengths and limitations of our approach. Our results suggest that promoting threshold from a hyperparameter to a parameter can effectively address the issue of dead neurons during training, resulting in a more robust training algorithm that leads to improved training convergence, increased test accuracy, and substantial reductions in the number of training epochs needed to achieve viable accuracy. Rouser achieves up to 70% lower training latency while providing up to 2% higher accuracy over state-of-the-art SNNs with similar network architecture on the neuromorphic datasets NMNIST, DVS128 and SHD.

翻译：在脉冲神经网络（SNNs）中，学习规则基于神经元的脉冲发放行为，即当神经元的膜电位超过其发放阈值时是否产生脉冲以及何时产生脉冲，这种脉冲时序编码了关键信息。然而，阈值通常被视为超参数，其选择不当可能导致神经元在训练的大部分时间内不发放脉冲，从而阻碍学习的有效速率。受生物神经元稳态机制的启发，本研究（Rouser）提出了一种通过循环内自适应阈值学习机制来激活训练中不活跃的神经元并改进SNN训练的方法。Rouser的自适应阈值能够根据输入数据和网络超参数进行动态调整，从而影响脉冲发放时序并改善训练效果。本研究主要探讨在SNN中同时学习神经元阈值与权重的重要性。我们在时空数据集NMNIST、DVS128和Spiking Heidelberg Digits（SHD）上评估Rouser的性能，将结果与最先进的SNN训练技术进行比较，并讨论本方法的优势与局限性。实验结果表明，将阈值从超参数提升为可学习参数，能够有效解决训练过程中的神经元“死亡”问题，从而形成一种更鲁棒的训练算法，带来训练收敛性的改善、测试精度的提升以及达到可行精度所需训练轮次的大幅减少。在神经形态数据集NMNIST、DVS128和SHD上，与具有相似网络架构的最先进SNN相比，Rouser在实现高达2%精度提升的同时，训练延迟降低了最高达70%。