.png){kind=icon}
返回
Gradient-based feature-attribution explainability methods for spiking neural networks
.png){kind=icon}
OA
AI
DOI：10.3389/fnins.2023.1153999.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
IntroductionSpiking neural networks (SNNs) are a model of computation that mimics the behavior of biological neurons. SNNs process event data (spikes) and operate more sparsely than artificial neural networks (ANNs), resulting in ultra-low latency and small power consumption. This paper aims to adapt and evaluate gradient-based explainability methods for SNNs, which were originally developed for conventional ANNs.MethodsThe adapted methods aim to create input feature attribution maps for SNNs trained through backpropagation that process either event-based spiking data or real-valued data. The methods address the limitations of existing work on explainability methods for SNNs, such as poor scalability, limited to convolutional layers, requiring the training of another model, and providing maps of activation values instead of true attribution scores. The adapted methods are evaluated on classification tasks for both real-valued and spiking data, and the accuracy of the proposed methods is confirmed through perturbation experiments at the pixel and spike levels.Results and discussionThe results reveal that gradient-based SNN attribution methods successfully identify highly contributing pixels and spikes with significantly less computation time than model-agnostic methods. Additionally, we observe that the chosen coding technique has a noticeable effect on the input features that will be most significant. These findings demonstrate the potential of gradient-based explainability methods for SNNs in improving our understanding of how these networks process information and contribute to the development of more efficient and accurate SNNs.
Keyword:
spiking neural networks
explainable artificial intelligence
XAI
brain-inspired computation
neuromorphic
event-based encoding
MNIST
CIFAR
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
A biologically plausible supervised learning method for spiking neural networks using the symmetric STDP rule使用对称STDP规则的尖峰神经网络的生物学合理监督学习方法.png)
NEURAL NETWORKSOAAI
NEURAL NETWORKSIF6.3
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
分享收藏分享收藏Networks of spiking neurons: The third generation of neural network models尖峰神经元网络: 第三代神经网络模型NEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏
查看更多内容