Visualize and Verify Deep Neural Networks
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, and deep dream.
You can use the Deep Network Designer app to build, visualize, and train deep learning networks interactively. You can then generate code to recreate network construction and training, and export trained networks to Simulink®.
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.
- Deep Network Designer App
Interactively create and train deep learning networks
- Visualization and Interpretability
Plot training progress, assess accuracy, explain predictions, and visualize features learned by a network
Train robust networks and verify network robustness