论文标题
强大而加速的单尖峰尖峰神经网络培训，适用于挑战时间任务
Robust and accelerated single-spike spiking neural network training with applicability to challenging temporal tasks
论文作者
论文摘要
尖峰神经网络（SNN），尤其是神经元最多一次尖峰的单个尖峰变体，比标准人工神经网络（ANN）更节能。但是，由于当前的解决方案要么缓慢或遭受训练不稳定性的影响，因此由于其动态和非不同的性质，很难训练单峰SSN。这些网络也因其有限的计算适用性而受到批评，例如不适合时间序列数据集。我们提出了一种新的模型，用于训练单峰值SNN，以减轻上述培训问题，并在各种图像和神经形态数据集合中获得竞争成果，与多型SPIKE SNN相比，高达$ 13.98 \ times $ thimes $培训的速度和最高$ 81 \％$ $ $ $。值得注意的是，我们的模型在涉及神经形态的时间序列数据集的具有挑战性的任务中以多峰值SNN的形式执行标准，这表明了单峰SNN比以前认为的更广泛的计算角色。
Spiking neural networks (SNNs), particularly the single-spike variant in which neurons spike at most once, are considerably more energy efficient than standard artificial neural networks (ANNs). However, single-spike SSNs are difficult to train due to their dynamic and non-differentiable nature, where current solutions are either slow or suffer from training instabilities. These networks have also been critiqued for their limited computational applicability such as being unsuitable for time-series datasets. We propose a new model for training single-spike SNNs which mitigates the aforementioned training issues and obtains competitive results across various image and neuromorphic datasets, with up to a $13.98\times$ training speedup and up to an $81\%$ reduction in spikes compared to the multi-spike SNN. Notably, our model performs on par with multi-spike SNNs in challenging tasks involving neuromorphic time-series datasets, demonstrating a broader computational role for single-spike SNNs than previously believed.
