Main Content

Visualization and Interpretability

Plot training progress, assess accuracy, explain predictions, and visualize features learned by a network

Monitor training progress using built-in plots of network accuracy and loss. Investigate trained networks using visualization techniques such as Grad-CAM, occlusion sensitivity, LIME, and deep dream.

Deep Learning Visualization Methods


Deep Network DesignerDesign, visualize, and train deep learning networks


trainingProgressMonitorMonitor and plot training progress for deep learning custom training loops


expand all

analyzeNetworkAnalyze deep learning network architecture
plotPlot neural network architecture
updateInfoUpdate information values for custom training loops
recordMetricsRecord metric values for custom training loops
groupSubPlotGroup metrics in training plot
activationsCompute deep learning network layer activations
confusionchartCreate confusion matrix chart for classification problem
sortClassesSort classes of confusion matrix chart
rocmetricsReceiver operating characteristic (ROC) curve and performance metrics for binary and multiclass classifiers
addMetricsCompute additional classification performance metrics
averageCompute performance metrics for average receiver operating characteristic (ROC) curve in multiclass problem
plotPlot receiver operating characteristic (ROC) curves and other performance curves
imageLIMEExplain network predictions using LIME
occlusionSensitivityExplain network predictions by occluding the inputs
deepDreamImageVisualize network features using deep dream
gradCAMExplain network predictions using Grad-CAM


ConfusionMatrixChart PropertiesConfusion matrix chart appearance and behavior
ROCCurve PropertiesReceiver operating characteristic (ROC) curve appearance and behavior


Training Progress and Performance