Optimising Event-Driven Spiking Neural Network with Regularisation and Cutoff

Dengyu Wu ^1,2* Gaojie Jin ^3,4 Han Yu ^5,6 Xinping Yi ⁷ Xiaowei Huang ¹

• ¹ University of Liverpool, Liverpool, United Kingdom
• ² King's College London, London, England, United Kingdom
• ³ State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences (CAS), Beijing, Beijing Municipality, China
• ⁴ University of Exeter, Exeter, England, United Kingdom
• ⁵ Chalmers University of Technology, Göteborg, Vastra Gotaland County, Sweden
• ⁶ Queen's University Belfast, Belfast, Northern Ireland, United Kingdom
• ⁷ Southeast University, Nanjing, Jiangsu Province, China

Spiking neural network (SNN), as the next generation of artificial neural network (ANN), offer a closer mimicry of natural neural networks and hold promise for significant improvements in computational efficiency. However, the current SNN is trained to infer over a fixed duration, overlooking the potential of dynamic inference in SNN. In this paper, we strengthen the marriage between SNN and event-driven processing with a proposal to consider a cutoff in SNN, which can terminate SNN anytime during inference to achieve efficient inference. Two novel optimisation techniques are presented to achieve inference efficient SNN: a Top-K cutoff and a regularisation.The proposed regularisation influences the training process, optimising SNN for the cutoff, while the Top-K cutoff technique optimises the inference phase. We conduct an extensive set of experiments on multiple benchmark frame-based datasets, such as CIFAR10/100, Tiny-ImageNet, and event-based datasets, including CIFAR10-DVS, N-Caltech101 and DVS128 Gesture. The experimental results demonstrate the effectiveness of our techniques in both ANN-to-SNN conversion and direct training, enabling SNNs to require 1.76 to 2.76 × fewer timesteps for CIFAR-10, while achieving 1.64 to 1.95× fewer timesteps across all event-based datasets, with near-zero accuracy loss. These findings affirms the compatibility and potential benefits of our techniques in enhancing accuracy and reducing inference latency when integrated with existing methods. Code available: https://github.com/Dengyu-Wu/SNNCutoff