# Optimising Event-Driven Spiking Neural Network with Regularisation and Cutoff

Source: [Optimising Event-Driven Spiking Neural Network with Regularisation and Cutoff](<https://www.sota2.com/research/paper/68fa76c51e209131cea6ee9c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:01:17.446Z

Authors: Dengyu Wu, Gaojie Jin, Han Yu, Xinping Yi, Xiaowei Huang

Published: 2023-01-23T16:14:09.000Z

## Abstract

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 asCIFAR10/100, 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 2.76x fewer timesteps for CIFAR-10, while achieving 1.64 to 1.95x 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

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2301.09522>)

[PDF](<https://arxiv.org/pdf/2301.09522.pdf>)
