用敏感性分析揭示神经网络决策关键输入，提升可解释性。
Application of Sensitivity Analysis Methods for Studying Neural Network Models
- 通过全局与局部敏感性分析定位关键输入特征
- 在糖尿病数据集上减少输入变量数而不损失精度
- 对比激活最大化与Grad-CAM，适用于医学图像解释
本研究展示了多种敏感性分析方法在神经网络对输入扰动的响应分析及机制解释中的应用能力。所考察的方法包括Sobol全局敏感性分析、输入像素局部敏感性分析和激活最大化技术。以一个小型前馈神经网络分析公开的临床糖尿病表格数据集，以及两个经典卷积架构VGG-16和ResNet-18用于图像分类任务为例。全局敏感性分析帮助识别小型神经网络的关键输入参数，并可在不显著降低准确率的情况下减少其数量。由于全局方法不适用于大型模型，本文对卷积神经网络采用局部敏感性分析与激活最大化方法，结果显示其在图像分类任务中呈现有趣模式。最后，将激活最大化结果与流行的Grad-CAM技术在超声数据分析中进行比较。
原文摘要 · Abstract (English)
This study demonstrates the capabilities of several methods for analyzing the sensitivity of neural networks to perturbations of the input data and interpreting their underlying mechanisms. The investigated approaches include the Sobol global sensitivity analysis, the local sensitivity method for input pixel perturbations and the activation maximization technique. As examples, in this study we consider a small feedforward neural network for analyzing an open tabular dataset of clinical diabetes data, as well as two classical convolutional architectures, VGG-16 and ResNet-18, which are widely used in image processing and classification. Utilization of the global sensitivity analysis allows us to identify the leading input parameters of the chosen tiny neural network and reduce their number without significant loss of the accuracy. As far as global sensitivity analysis is not applicable to larger models we try the local sensitivity analysis and activation maximization method in application to the convolutional neural networks. These methods show interesting patterns for the convolutional models solving the image classification problem. All in all, we compare the results of the activation maximization method with popular Grad-CAM technique in the context of ultrasound data analysis.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。