Visualisierung und Verifikation

Visualisierung des Verhaltens neuronaler Netze, Erklärung von Vorhersagen und Überprüfung der Robustheit anhand von Sequenz- und Tabellendaten

Visualisieren Sie tiefe Netze während und nach dem Training. Überwachen Sie den Trainingsfortschritt mithilfe integrierter Netzgenauigkeits- und Netzverlustdiagramme. Um trainierte Netze zu untersuchen, können Sie Visualisierungstechniken wie Grad-CAM verwenden.

Verwenden Sie Deep-Learning-Verifikationsmethoden zur Bewertung der Eigenschaften von tiefen neuronalen Netzen. So können Sie beispielsweise die Robustheitseigenschaften eines Netzes überprüfen, Ausgangsgrenzen des Netzes berechnen und manipulierte Beispiele finden.

Apps

Deep Network Designer

Entwurf und Visualisierung von Deep-Learning-Netzen

Funktionen

alle erweitern

Diagramme

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

Visualisierung von Merkmalen

`predict`	Compute deep learning network output for inference
`minibatchpredict`	Mini-batched neural network prediction (Seit R2024a)
`scores2label`	Convert prediction scores to labels (Seit R2024a)
`gradCAM`	Explain network predictions using Grad-CAM (Seit 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 (Seit R2022b)
`addMetrics`	Compute additional classification performance metrics (Seit R2022b)
`average`	Compute performance metrics for average receiver operating characteristic (ROC) curve in multiclass problem (Seit R2022b)

Eigenschaften

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

Themen

Interpretierbarkeit

Visualize Activations of LSTM Network
This example shows how to investigate and visualize the features learned by LSTM networks by extracting the activations.
Interpret Deep Learning Time-Series Classifications Using Grad-CAM
This example shows how to 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.
View Network Behavior Using tsne
This example shows how to use the tsne function to view activations in a trained network.
Deep Learning in MATLAB
Discover deep learning capabilities in MATLAB^® using convolutional neural networks for classification and regression, including pretrained networks and transfer learning, and training on GPUs, CPUs, clusters, and clouds.
Deep Learning Tips and Tricks
Learn how to improve the accuracy of deep learning networks.

Trainingsfortschritt und Leistung

Überwachen des Deep-Learning-Trainingsfortschritts
Dieses Beispiel zeigt, wie man den Trainingsfortschritt von Deep-Learning-Netzen überwachen kann.
Monitor Custom Training Loop Progress
Track and plot custom training loop progress.
ROC Curve and Performance Metrics
Use rocmetrics to examine the performance of a classification algorithm on a test data set.

Enthaltene Beispiele

Investigate Spectrogram Classifications Using LIME

Use locally interpretable model-agnostic explanations (LIME) to investigate the robustness of a deep convolutional neural network trained to classify spectrograms. LIME is a technique for visualizing which parts of an observation contribute to the classification decision of a network. This example uses the imageLIME function to understand which features in the spectrogram data are most important for classification.

Live Script öffnen

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.

Live Script öffnen

Time Series Forecasting Using Deep Learning

Forecast time series data using a long short-term memory (LSTM) network.

Live Script öffnen

Train Speech Command Recognition Model Using Deep Learning

Train a deep learning model that detects the presence of speech commands in audio. The example uses the Speech Commands Dataset [1] to train a convolutional neural network to recognize a set of commands.

Live Script öffnen

Chemical Process Fault Detection Using Deep Learning

Use simulation data to train a neural network than can detect faults in a chemical process.

Live Script öffnen