Unifying Activation- and Timing-based Learning Rules for Spiking Neural Networks
This work addresses a specific challenge in SNN training for researchers in neuromorphic computing, but it is incremental as it builds on existing methods.
The paper tackled the problem of training Spiking Neural Networks (SNNs) by unifying activation-based and timing-based gradient computation methods, proposing a new supervised learning approach that combines both to utilize spikes more effectively, resulting in higher accuracy and efficiency compared to previous methods.
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.