La traduction de cette page n'est pas à jour. Cliquez ici pour voir la dernière version en anglais.

Visualisation du Deep Learning

Tracer la progression de l’apprentissage, évaluer la précision, expliquer les prédictions et visualiser les caractéristiques apprises par un réseau

Surveillez la progression de l’apprentissage en utilisant des tracés prédéfinis des fonctions de précision et de perte du réseau. Analysez des réseaux entraînés avec des techniques de visualisation comme Grad-CAM, la sensibilité aux occlusions, LIME et DeepDream.

Applications

Deep Network Designer

Concevoir, visualiser et entraîner des réseaux de Deep Learning

Objets

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

Fonctions

développer tout

Tracés

`analyzeNetwork`	Analyze deep learning network architecture
`plot`	Plot neural network architecture
`updateInfo`	Update information values for custom training loops (depuis R2022b)
`recordMetrics`	Record metric values for custom training loops (depuis R2022b)
`groupSubPlot`	Group metrics in training plot (depuis R2022b)

Visualisation et prédiction des caractéristiques

`activations`	(Not recommended) Compute deep learning network layer activations
`predict`	(Not recommended) Predict responses using trained deep learning neural network
`classify`	(Not recommended) Classify data using trained deep learning neural network
`predictAndUpdateState`	(Not recommended) Predict responses using a trained recurrent neural network and update the network state
`classifyAndUpdateState`	(Not recommended) Classify data using a trained recurrent neural network and update the network state
`resetState`	Reset state parameters of neural network
`deepDreamImage`	Visualize network features using deep dream
`occlusionSensitivity`	Explain network predictions by occluding the inputs (depuis R2019b)
`imageLIME`	Explain network predictions using LIME (depuis R2020b)
`gradCAM`	Explain network predictions using Grad-CAM (depuis R2021a)
`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 (depuis R2022b)
`addMetrics`	Compute additional classification performance metrics (depuis R2022b)
`average`	Compute performance metrics for average receiver operating characteristic (ROC) curve in multiclass problem (depuis R2022b)
`plot`	Plot receiver operating characteristic (ROC) curves and other performance curves (depuis R2022b)

Propriétés

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

Rubriques

Classify Webcam Images Using Deep Learning
This example shows how to classify images from a webcam in real time using the pretrained deep convolutional neural network GoogLeNet.
Surveiller la progression de l'apprentissage du Deep Learning
Cet exemple montre comment surveiller le processus d’apprentissage des réseaux de Deep Learning.
Monitor Custom Training Loop Progress
Track and plot custom training loop progress.
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.
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.
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 Activations of LSTM Network
This example shows how to investigate and visualize the features learned by LSTM networks by extracting the activations.
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.
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.

Exemples présentés

Detect Vanishing Gradients in Deep Neural Networks by Plotting Gradient Distributions

Monitor vanishing gradients while training a deep neural network.

Ouvrir le live script

Explore Network Predictions Using Deep Learning Visualization Techniques

Investigate network predictions using deep learning visualization techniques.

Ouvrir le 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.

Ouvrir le 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.

Ouvrir le 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.

Ouvrir le live script

Explore Semantic Segmentation Network Using Grad-CAM

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

Ouvrir le 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.

Ouvrir le live script

Deep Dream Images Using GoogLeNet

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

Ouvrir le live script