Unleashing the Potential of Spiking Neural Networks by Dynamic Confidence
This addresses the efficiency problem for SNN applications, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the accuracy-latency trade-off in spiking neural networks (SNNs) by introducing Dynamic Confidence, a method that decodes confidence information to dynamically terminate inferences, achieving a 40% average speedup on CIFAR-10 and ImageNet and enabling a ResNet-50 SNN to reach 82.47% accuracy on ImageNet in 4.71 average time steps.
This paper presents a new methodology to alleviate the fundamental trade-off between accuracy and latency in spiking neural networks (SNNs). The approach involves decoding confidence information over time from the SNN outputs and using it to develop a decision-making agent that can dynamically determine when to terminate each inference. The proposed method, Dynamic Confidence, provides several significant benefits to SNNs. 1. It can effectively optimize latency dynamically at runtime, setting it apart from many existing low-latency SNN algorithms. Our experiments on CIFAR-10 and ImageNet datasets have demonstrated an average 40% speedup across eight different settings after applying Dynamic Confidence. 2. The decision-making agent in Dynamic Confidence is straightforward to construct and highly robust in parameter space, making it extremely easy to implement. 3. The proposed method enables visualizing the potential of any given SNN, which sets a target for current SNNs to approach. For instance, if an SNN can terminate at the most appropriate time point for each input sample, a ResNet-50 SNN can achieve an accuracy as high as 82.47% on ImageNet within just 4.71 time steps on average. Unlocking the potential of SNNs needs a highly-reliable decision-making agent to be constructed and fed with a high-quality estimation of ground truth. In this regard, Dynamic Confidence represents a meaningful step toward realizing the potential of SNNs.