New preprint for #neuromorphic and #SpikingNeuralNetwork folk (with Pengfei Sun and awesome MSc student Ziqiao Yu).
https://arxiv.org/abs/2507.16043
Surrogate gradients are popular for training SNNs, but some worry whether they really learn complex temporal spike codes. TLDR: we tested this, and yes they can!
We also find that delay-based spiking neural networks seem to degrade in more human-like ways than networks without delays.
Check the next post for links to the code and dataset which you can easily use to test your own spike based learning algorithms and models.
arXiv.orgBeyond Rate Coding: Surrogate Gradients Enable Spike Timing Learning in Spiking Neural NetworksWe investigate the extent to which Spiking Neural Networks (SNNs) trained with Surrogate Gradient Descent (Surrogate GD), with and without delay learning, can learn from precise spike timing beyond firing rates. We first design synthetic tasks isolating intra-neuron inter-spike intervals and cross-neuron synchrony under matched spike counts. On more complex spike-based speech recognition datasets (Spiking Heidelberg Digits (SHD) and Spiking Speech Commands (SSC), we construct variants where spike count information is eliminated and only timing information remains, and show that Surrogate GD-trained SNNs are able to perform significantly above chance whereas purely rate-based models perform at chance level. We further evaluate robustness under biologically inspired perturbations -- including Gaussian jitter per spike or per-neuron, and spike deletion -- revealing consistent but perturbation-specific degradation. Networks show a sharp performance drop when spike sequences are reversed in time, with a larger drop in performance from SNNs trained with delays, indicating that these networks are more human-like in terms of behaviour. To facilitate further studies of temporal coding, we have released our modified SHD and SSC datasets.
