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

Apps

Deep Network DesignerDesign, visualize, and train deep learning networks

Objekte

trainingProgressMonitorMonitor and plot training progress for deep learning custom training loops (Seit R2022b)

Funktionen

alle erweitern

analyzeNetworkAnalyze deep learning network architecture
plotPlot neural network architecture
updateInfoUpdate information values for custom training loops (Seit R2022b)
recordMetricsRecord metric values for custom training loops (Seit R2022b)
groupSubPlotGroup metrics in training plot (Seit R2022b)
accuracyMetricDeep learning accuracy metric (Seit R2023b)
aucMetricDeep learning area under ROC curve (AUC) metric (Seit R2023b)
fScoreMetricDeep learning F-score metric (Seit R2023b)
precisionMetricDeep learning precision metric (Seit R2023b)
recallMetricDeep learning recall metric (Seit R2023b)
rmseMetricDeep learning root mean squared error metric (Seit R2023b)
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 (Seit R2022b)
addMetricsCompute additional classification performance metrics (Seit R2022b)
averageCompute performance metrics for average receiver operating characteristic (ROC) curve in multiclass problem (Seit R2022b)
plotPlot receiver operating characteristic (ROC) curves and other performance curves (Seit R2022b)
imageLIMEExplain network predictions using LIME (Seit R2020b)
occlusionSensitivityExplain network predictions by occluding the inputs (Seit R2019b)
deepDreamImageVisualize network features using deep dream
gradCAMExplain network predictions using Grad-CAM (Seit R2021a)

Eigenschaften

ConfusionMatrixChart PropertiesConfusion matrix chart appearance and behavior
ROCCurve PropertiesReceiver operating characteristic (ROC) curve appearance and behavior (Seit R2022b)

Themen

Training Progress and Performance

Interpretability