.png){kind=icon}
返回
Optimizing event-driven spiking neural network with regularization and cutoff
.png){kind=icon}
OA
AI
DOI：10.3389/fnins.2025.1522788.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Spiking neural networks (SNNs), which are the next generation of artificial neural networks (ANNs), offer a closer mimicry to natural neural networks and hold promise for significant improvements in computational efficiency. However, the current SNN model is trained to infer over a fixed duration, thereby overlooking the potential for dynamic inference in the SNN model. In this paper, we strengthen the relationship between SNN and event-driven processing by proposing the inclusion of a cutoff in SNN, that can terminate SNN at any time during inference to achieve efficient inference. Two novel optimization techniques are presented to achieve an inference-efficient SNN: a Top-K cutoff and regularization. The proposed regularization influences the training process by optimizing the SNN for the cutoff, whereas the Top-K cutoff technique optimizes the inference phase. We conducted 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 the proposed techniques in both the ANN-to-SNN conversion and direct training, enabling SNNs to require 1.76 to 2.76 x 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 affirm the compatibility and potential benefits of the proposed techniques in terms of enhancing accuracy and reducing inference latency when integrated with existing methods. Code available: https://github.com/Dengyu-Wu/SNNCutoff.
Keyword:
spiking neural network
ANN-to-SNN conversion
SNN regularization
SNN cutoff
adaptive inference
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.2
论文数:
1.6W
被引数:
5.3W
机构
引用论文
Measurement of Seasonal Indoor Radon Concentration in Sakarya University, Turkey土耳其萨卡里亚大学室内季节性氡浓度测量
OAAI
OAAI分享收藏Revisiting Batch Normalization for Training Low-Latency Deep Spiking Neural Networks From ScratchOAAI
OAAI分享收藏Contributions of evacuation proctography and anorectal manometry to evaluation of adults with constipation and defecatory difficulty排空直肠造影和肛门直肠测压对成人便秘和排便困难的评估的贡献
PREAI
分享收藏Enhancement and Fusion of Multi-Scale Feature Maps for Small Object Detection用于小目标检测的多尺度特征图增强与融合
PREAI
分享收藏Concentration of uranium in human cancerous tissues of Southern Iraqi patients using fission track analysis使用裂变径迹分析法测定南伊拉克患者人体癌组织中铀的浓度
PREAI
分享收藏Tentamen florae Germanicae; continens enumerationem plantarum in Germania sponte nascentium《德国植物志考试》；包含在德国自然生长的植物的列举.png)
OAAI
IF0
OAAI分享收藏
查看更多内容