论文标题
统一基于激活和计时的学习规则
Unifying Activation- and Timing-based Learning Rules for Spiking Neural Networks
论文作者
论文摘要
对于尖峰神经网络（SNN）训练中时域的梯度计算，已经独立研究了两种不同的方法。第一个是计算有关尖峰激活的变化（基于激活的方法）的梯度，第二个是计算峰值变化的梯度（基于时序的方法）。在这项工作中，我们介绍了两种方法的比较研究，并提出了一种将它们结合在一起的新的监督学习方法。所提出的方法通过移动尖峰时序，如基于时序的方法，以及在基于激活的方法中一样生成和去除尖峰，从而更有效地利用了每个单独的尖峰。实验结果表明，所提出的方法在准确性和效率方面都比以前的方法获得更高的性能。
For the gradient computation across the time domain in Spiking Neural Networks (SNNs) training, two different approaches have been independently studied. The first is to compute the gradients with respect to the change in spike activation (activation-based methods), and the second is to compute the gradients with respect to the change in spike timing (timing-based methods). In this work, we present a comparative study of the two methods and propose a new supervised learning method that combines them. The proposed method utilizes each individual spike more effectively by shifting spike timings as in the timing-based methods as well as generating and removing spikes as in the activation-based methods. Experimental results showed that the proposed method achieves higher performance in terms of both accuracy and efficiency than the previous approaches.
