Spiking Neural Network (SNN) is acknowledged as the next generation of
Artificial Neural Network (ANN) and hold great promise in effectively
processing spatial-temporal information. However, the choice of timestep
becomes crucial as it significantly impacts the accuracy of the neural network
training. Specifically, a smaller timestep indicates better performance in
efficient computing, resulting in reduced latency and operations. While, using
a small timestep may lead to low accuracy due to insufficient information
presentation with few spikes. This observation motivates us to develop an SNN
that is more reliable for adaptive timestep by introducing a novel
regularisation technique, namely Spatial-Temporal Regulariser (STR). Our
approach regulates the ratio between the strength of spikes and membrane
potential at each timestep. This effectively balances spatial and temporal
performance during training, ultimately resulting in an Anytime Optimal
Inference (AOI) SNN. Through extensive experiments on frame-based and
event-based datasets, our method, in combination with cutoff based on softmax
output, achieves state-of-the-art performance in terms of both latency and
accuracy. Notably, with STR and cutoff, SNN achieves 2.14 to 2.89 faster in
inference compared to the pre-configured timestep with near-zero accuracy drop
of 0.50% to 0.64% over the event-based datasets. Code available:
this https URL

使用新颖的空时正则化技术 Spatial-Temporal Regulariser（STR）开发的一种适应性时间步间隔的脉冲神经网络（Spiking Neural Network，SNN），通过在每个时间步中调整脉冲强度和膜电位之间的比例，有效平衡了训练过程中的空间和时间性能，最终实现了全时最优推理（Anytime Optimal Inference，AOI）SNN，在基于帧和事件的数据集上与 softmax 输出截断相结合，达到了最先进的延迟和准确性。