可视化和验证深度神经网络

Investigate network predictions using deep learning visualization techniques.

Use the gradient-weighted class activation mapping (Grad-CAM) technique to understand why a deep learning network makes its classification decisions. Grad-CAM, invented by Selvaraju and coauthors [1], uses the gradient of the classification score with respect to the convolutional features determined by the network in order to understand which parts of the image are most important for classification. This example uses the GoogLeNet pretrained network for images.

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.

Use locally interpretable model-agnostic explanations (LIME) to understand why a deep neural network makes a classification decision.

此示例说明如何使用深度网络设计器创建和训练简单的卷积神经网络来进行深度学习分类。卷积神经网络是深度学习的基本工具，尤其适用于图像识别。

Use the fast gradient sign method (FGSM) and the basic iterative method (BIM) to generate adversarial examples for a pretrained neural network.

Verify the adversarial robustness of a deep learning neural network.

Monitor vanishing gradients while training a deep neural network.