可视化和验证深度神经网络
R2026b在训练期间和训练后，可视化深度网络。使用内置的网络准确度和损失图或通过指定自定义度量监控训练进度。使用可视化和可解释性方法，如 Grad-CAM、遮挡敏感度、LIME、Deep Dream 和 D-RISE 研究经过训练的网络。
使用深度学习验证方法来评估深度神经网络的属性。例如，您可以验证网络的稳健性属性、计算网络输出边界、查找对抗样本以及检测分布外数据。
精选示例
Explore Network Predictions Using Deep Learning Visualization Techniques
Investigate network predictions using deep learning visualization techniques.
Grad-CAM 揭示深度学习决策背后的原因
此示例说明如何使用梯度加权类激活映射 (Grad-CAM) 技术来理解深度学习网络做出相应分类决策的原因。Grad-CAM 由 Selvaraju 及其合著者提出 [1]，该技术利用分类得分相对于网络确定的卷积特征的梯度，来理解图像中哪些部分对分类最为重要。此示例使用适用于图像的 GoogLeNet 预训练网络。
Interpret Deep Learning Time-Series Classifications Using Grad-CAM
Use the gradient-weighted class activation mapping (Grad-CAM) technique to understand the classification decisions of a 1-D convolutional neural network trained on time-series data.
Understand Network Predictions Using LIME
Use locally interpretable model-agnostic explanations (LIME) to understand why a deep neural network makes a classification decision.
Build Simple App for Deep Learning Inference Using App Designer
Use App Designer to create an app that can classify images using a deep neural network. You can modify the app for other types of deep learning inference, for example, sequence classification or image regression.
Generate Untargeted and Targeted Adversarial Examples for Image Classification
Use the fast gradient sign method (FGSM) and the basic iterative method (BIM) to generate adversarial examples for a pretrained neural network.
Verify Robustness of Deep Learning Neural Network
Verify the adversarial robustness of a deep learning neural network.
Detect Vanishing Gradients in Deep Neural Networks by Plotting Gradient Distributions
Monitor vanishing gradients while training a deep neural network.
