Spiking Neural Networks (SNNs) are biologically-inspired deep neural networks that efficiently extract temporal information while offering promising gains in terms of energy efficiency and latency when deployed on neuromorphic devices. However, SNN model parameters are sensitive to temporal resolution, leading to significant performance drops when the temporal resolution of target data at the edge is not the same with that of the pre-deployment source data used for training, especially when fine-tuning is not possible at the edge. To address this challenge, we propose three novel domain adaptation methods for adapting neuron parameters to account for the change in time resolution without re-training on target time-resolution. The proposed methods are based on a mapping between neuron dynamics in SNNs and State Space Models (SSMs); and are applicable to general neuron models. We evaluate the proposed methods under spatio-temporal data tasks, namely the audio keyword spotting datasets SHD and MSWC as well as the image classification NMINST dataset. Our methods provide an alternative to - and in majority of the cases significantly outperform - the existing reference method that simply scales the time constant. Moreover, our results show that high accuracy on high temporal resolution data can be obtained by time efficient training on lower temporal resolution data and model adaptation.

翻译：脉冲神经网络（SNNs）是一种受生物学启发的深度神经网络，能够高效提取时序信息，同时在部署于神经形态设备时，在能效和延迟方面展现出显著优势。然而，SNN模型参数对时间分辨率极为敏感，当边缘设备上目标数据的时间分辨率与训练所用的预部署源数据不一致时，会导致性能显著下降，尤其是在边缘端无法进行微调的情况下。为应对这一挑战，我们提出了三种新颖的域适应方法，用于调整神经元参数以适应时间分辨率的变化，而无需在目标时间分辨率上重新训练。所提方法基于SNN中神经元动力学与状态空间模型（SSMs）之间的映射关系，适用于通用的神经元模型。我们在时空数据任务中评估了所提方法，包括音频关键词识别数据集SHD和MSWC，以及图像分类数据集NMINST。我们的方法为现有仅简单缩放时间常数的参考方法提供了替代方案，且在大多数情况下显著优于后者。此外，实验结果表明，通过在较低时间分辨率数据上进行时间高效的训练并结合模型适应，可以在高时间分辨率数据上获得高精度。