Diese Seite ist für die vorige Version. Die entsprechende englische Seite wurde in der aktuellen Version entfernt.
Visualisierung und Verifikation
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
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 thetsnefunction 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
Userocmetricsto 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.
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.
Zeitreihen-Vorhersagen mit Deep Learning
Dieses Beispiel veranschaulicht, wie Sie Zeitreihendaten mithilfe eines LSTM-Netzes (Long-Short-Term-Memory, langes Kurzzeitgedächtnis) vorhersagen können.
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.
Chemical Process Fault Detection Using Deep Learning
Use simulation data to train a neural network than can detect faults in a chemical process.
