Spiking Neural Networks (SNNs) have gained significant attention as a potentially energy-efficient alternative for standard neural networks with their sparse binary activation. However, SNNs suffer from memory and computation overhead due to spatio-temporal dynamics and multiple backpropagation computations across timesteps during training. To address this issue, we introduce Tensor Train Decomposition for Spiking Neural Networks (TT-SNN), a method that reduces model size through trainable weight decomposition, resulting in reduced storage, FLOPs, and latency. In addition, we propose a parallel computation pipeline as an alternative to the typical sequential tensor computation, which can be flexibly integrated into various existing SNN architectures. To the best of our knowledge, this is the first of its kind application of tensor decomposition in SNNs. We validate our method using both static and dynamic datasets, CIFAR10/100 and N-Caltech101, respectively. We also propose a TT-SNN-tailored training accelerator to fully harness the parallelism in TT-SNN. Our results demonstrate substantial reductions in parameter size (7.98X), FLOPs (9.25X), training time (17.7%), and training energy (28.3%) during training for the N-Caltech101 dataset, with negligible accuracy degradation.

翻译：脉冲神经网络（SNNs）因其稀疏的二值激活特性，作为标准神经网络的一种潜在高能效替代方案而受到广泛关注。然而，由于时空动态特性以及训练过程中跨时间步的多重反向传播计算，SNNs存在内存和计算开销过大的问题。为解决此问题，我们提出了用于脉冲神经网络的张量链分解方法（TT-SNN）。该方法通过可训练的权重分解来减小模型规模，从而降低存储需求、浮点运算量（FLOPs）和延迟。此外，我们提出了一种并行计算流程，以替代典型的顺序张量计算，该流程可以灵活地集成到各种现有的SNN架构中。据我们所知，这是张量分解在SNNs中的首次应用。我们分别在静态数据集（CIFAR10/100）和动态数据集（N-Caltech101）上验证了我们的方法。我们还提出了一种专为TT-SNN设计的训练加速器，以充分利用TT-SNN中的并行性。实验结果表明，在N-Caltech101数据集上训练时，我们的方法能显著减少参数量（7.98倍）、浮点运算量（9.25倍）、训练时间（17.7%）和训练能耗（28.3%），且精度损失可忽略不计。