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

Flow chart showing methods used to visualize the predictions made by a trained network. The visualization methods can be used for verification, debugging, learning, detecting bias, and model selection.

Deep Learning Visualization Methods

App

Deep Network Designer

Progetta, visualizza e addestra le reti di Deep Learning

Oggetti

trainingProgressMonitor Monitor and plot training progress for deep learning custom training loops (Da R2022b)

Funzioni

espandi tutto

Network

`analyzeNetwork`	Analyze deep learning network architecture
`plot`	Plot neural network architecture

Training Progress

`updateInfo`	Update information values for custom training loops (Da R2022b)
`recordMetrics`	Record metric values for custom training loops (Da R2022b)
`groupSubPlot`	Group metrics in training plot (Da R2022b)
`yscale`	Set training plot y-axis scale (linear or logarithmic) (Da R2024a)

Metrics

`accuracyMetric`	Deep learning accuracy metric (Da R2023b)
`aucMetric`	Deep learning area under ROC curve (AUC) metric (Da R2023b)
`fScoreMetric`	Deep learning F-score metric (Da R2023b)
`precisionMetric`	Deep learning precision metric (Da R2023b)
`recallMetric`	Deep learning recall metric (Da R2023b)
`rmseMetric`	Deep learning root mean squared error metric (Da R2023b)

Prediction

`predict`	Compute deep learning network output for inference (Da R2019b)
`minibatchpredict`	Mini-batched neural network prediction (Da R2024a)
`scores2label`	Convert prediction scores to labels (Da R2024a)
`confusionchart`	Create confusion matrix chart for classification problem
`sortClasses`	Sort classes of confusion matrix chart
`rocmetrics`	Receiver operating characteristic (ROC) curve and performance metrics for binary and multiclass classifiers (Da R2022b)
`addMetrics`	Compute additional classification performance metrics (Da R2022b)
`average`	Compute performance metrics for average receiver operating characteristic (ROC) curve in multiclass problem (Da R2022b)
`plot`	Plot receiver operating characteristic (ROC) curves and other performance curves (Da R2022b)

Interpretability

`imageLIME`	Explain network predictions using LIME (Da R2020b)
`occlusionSensitivity`	Explain network predictions by occluding the inputs (Da R2019b)
`deepDreamImage`	Visualize network features using deep dream
`gradCAM`	Explain network predictions using Grad-CAM (Da R2021a)
`drise`	Explain object detection network predictions using D-RISE (Da R2024a)

Proprietà

ConfusionMatrixChart Properties	Confusion matrix chart appearance and behavior
ROCCurve Properties	Receiver operating characteristic (ROC) curve appearance and behavior (Da R2022b)

Argomenti

Training Progress and Performance

Monitoraggio dei progressi dell’addestramento in Deep Learning
Questo esempio mostra come monitorare il processo di addestramento delle reti di Deep Learning.
Monitor Custom Training Loop Progress
Track and plot custom training loop progress.
Monitor GAN Training Progress and Identify Common Failure Modes
Learn how to diagnose and fix some of the most common failure modes in GAN training.
ROC Curve and Performance Metrics
Use rocmetrics to examine the performance of a classification algorithm on a test data set.
Compare Deep Learning Models Using ROC Curves
This example shows how to use receiver operating characteristic (ROC) curves to compare the performance of deep learning models.
Define Custom Metric Function
Define custom deep learning metrics using functions.
Define Custom Deep Learning Metric Object
Learn how to define custom deep learning metrics using custom classes.
Define Custom F-Beta Score Metric Object
This example shows how to define a generic F-beta score metric.

Interpretability

Explore Network Predictions Using Deep Learning Visualization Techniques
This example shows how to investigate network predictions using deep learning visualization techniques.
Understand Network Predictions Using Occlusion
This example shows how to use occlusion sensitivity maps to understand why a deep neural network makes a classification decision.
Interpret Deep Network Predictions on Tabular Data Using LIME
This example shows how to use the locally interpretable model-agnostic explanations (LIME) technique to understand the predictions of a deep neural network classifying tabular data.
Investigate Spectrogram Classifications Using LIME
This example shows how to use locally interpretable model-agnostic explanations (LIME) to investigate the robustness of a deep convolutional neural network trained to classify spectrograms.
Investigate Classification Decisions Using Gradient Attribution Techniques
This example shows how to use gradient attribution maps to investigate which parts of an image are most important for classification decisions made by a deep neural network.
Investigate Network Predictions Using Class Activation Mapping
This example shows how to use class activation mapping (CAM) to investigate and explain the predictions of a deep convolutional neural network for image classification.
Visualize Image Classifications Using Maximal and Minimal Activating Images
This example shows how to use a data set to find out what activates the channels of a deep neural network.
View Network Behavior Using tsne
This example shows how to use the tsne function to view activations in a trained network.
Visualizzazione delle attivazioni della rete LSTM
Questo esempio mostra come analizzare e visualizzare le feature apprese dalle reti LSTM tramite l'estrazione delle attivazioni.
Visualize Activations of a Convolutional Neural Network
This example shows how to feed an image to a convolutional neural network and display the activations of different layers of the network.
Visualize Features of a Convolutional Neural Network
This example shows how to visualize the features learned by convolutional neural networks.
Deep Learning Visualization Methods
Learn about and compare deep learning visualization methods.

Esempi in primo piano

Detect Vanishing Gradients in Deep Neural Networks by Plotting Gradient Distributions

Monitor vanishing gradients while training a deep neural network.

Apri live script

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.

Apri live script

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.

Apri live script

Understand Network Predictions Using LIME

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

Apri live script

Explore Semantic Segmentation Network Using Grad-CAM

Explore the predictions of a pretrained semantic segmentation network using Grad-CAM.

Apri live script

Investigate Audio Classifications Using Deep Learning Interpretability Techniques

Use interpretability techniques to investigate the predictions of a deep neural network trained to classify audio data.

Apri live script

Deep Dream Images Using GoogLeNet

Generate images using deepDreamImage with the pretrained convolutional neural network GoogLeNet.

Apri live script

Detect Issues During Deep Neural Network Training

Automatically detect issues while training a deep neural network.

Apri live script

Explore Quantized Semantic Segmentation Network Using Grad-CAM

Compare the predictions of a quantized semantic segmentation network to the original network using the gradient-weighted class activation mapping (Grad-CAM) interpretability method.

Apri live script