Visualize and Verify Deep Neural Networks

Visualize network behavior, explain predictions, and verify robustness

Visualize deep networks during and after training. Monitor training progress using built-in plots of network accuracy and loss, or by specifying custom metrics. Investigate trained networks using visualization and interpretability techniques such as Grad-CAM, occlusion sensitivity, LIME, deep dream, and D-RISE.

Use deep learning verification methods to assess the properties of deep neural networks. For example, you can verify the robustness properties of a network, compute network output bounds, find adversarial examples, and detect out-of-distribution data.

Categories

Featured Examples

Explore Network Predictions Using Deep Learning Visualization Techniques

Explore Network Predictions Using Deep Learning Visualization Techniques

Investigate network predictions using deep learning visualization techniques.

Grad-CAM Reveals the Why Behind Deep Learning Decisions

Grad-CAM Reveals the Why Behind Deep Learning Decisions

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.

Interpret Deep Learning Time-Series Classifications Using Grad-CAM

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

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

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

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 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

Detect Vanishing Gradients in Deep Neural Networks by Plotting Gradient Distributions

Monitor vanishing gradients while training a deep neural network.