Apprentissage prédéfini

Entraîner des réseaux de Deep Learning pour des données séquentielles et tabulaires avec des fonctions d’apprentissage prédéfinies

Après avoir défini l’architecture du réseau, vous pouvez définir des paramètres d’apprentissage avec la fonction trainingOptions. Vous pouvez ensuite entraîner le réseau avec la fonction trainnet. Utilisez le réseau entraîné pour prédire des étiquettes de classe ou des réponses numériques ou pour prévoir de futurs pas de temps.

Vous pouvez entraîner un réseau de neurones sur un CPU, un GPU, plusieurs CPU ou GPU ou bien en parallèle sur un cluster ou dans le cloud. L’apprentissage sur un GPU ou en parallèle nécessite Parallel Computing Toolbox™. L’utilisation d’un GPU nécessite un dispositif GPU supporté (pour plus d'information sur les dispositifs supportés, veuillez consulter GPU Computing Requirements (Parallel Computing Toolbox)). Spécifiez l’environnement d’exécution avec la fonction trainingOptions.

Applications

Deep Network Designer

Concevoir et visualiser des réseaux de Deep Learning

Fonctions

développer tout

Entraîner le réseau

`trainingOptions`	Options d’un réseau de neurones d’apprentissage pour le Deep Learning
`trainnet`	Train deep learning neural network (depuis R2023b)
`analyzeNetwork`	Analyze deep learning network architecture

Prédiction

`predict`	Compute deep learning network output for inference (depuis R2019b)
`minibatchpredict`	Mini-batched neural network prediction (depuis R2024a)
`scores2label`	Convert prediction scores to labels (depuis R2024a)
`confusionchart`	Create confusion matrix chart for classification problem
`sortClasses`	Sort classes of confusion matrix chart

Rubriques

Réseaux perceptron multicouches

Train Network with Numeric Features
This example shows how to create and train a simple neural network for deep learning feature data classification.
Compare Deep Learning Networks for Credit Default Prediction
Create, train, and compare three deep learning networks for predicting credit default probability.
Battery State of Charge Workflow

An example workflow for training, compressing, and using a deep learning network in Simulink^®.
- ÉTAPE 1: Predict Battery State of Charge Using Deep Learning
- ÉTAPE 2: Compress Network for Estimating Battery State of Charge
- ÉTAPE 3: Battery State of Charge Estimation in Simulink Using Deep Learning Network

Réseaux récurrents

Sequence-to-Sequence Classification Using Deep Learning
This example shows how to classify each time step of sequence data using a long short-term memory (LSTM) network.
Sequence-to-Sequence Regression Using Deep Learning
This example shows how to predict the remaining useful life (RUL) of engines by using deep learning.
Sequence-to-One Regression Using Deep Learning
This example shows how to predict the frequency of a waveform using a long short-term memory (LSTM) neural network.
Train Network with LSTM Projected Layer
Train a deep learning network with an LSTM projected layer for sequence-to-label classification.
Classify Videos Using Deep Learning
This example shows how to create a network for video classification by combining a pretrained image classification model and an LSTM network.
Train Network Using Custom Mini-Batch Datastore for Sequence Data
This example shows how to train a deep learning network on out-of-memory sequence data using a custom mini-batch datastore.

Réseaux à convolution

Sequence Classification Using 1-D Convolutions
This example shows how to classify sequence data using a 1-D convolutional neural network.
Time Series Anomaly Detection Using Deep Learning
This example shows how to detect anomalies in sequence or time series data.
Train Sequence Classification Network Using Data With Imbalanced Classes
This example shows how to classify sequences with a 1-D convolutional neural network using class weights to modify the training to account for imbalanced classes.
Sequence-to-Sequence Classification Using 1-D Convolutions
This example shows how to classify each time step of sequence data using a generic temporal convolutional network (TCN).
Train Network with Complex-Valued Data
This example shows how to predict the frequency of a complex-valued waveform using a 1-D convolutional neural network.
Sequence Classification Using CNN-LSTM Network
This example shows how to create a 2-D CNN-LSTM network for speech classification tasks by combining a 2-D convolutional neural network (CNN) with a long short-term memory (LSTM) layer.
Train Network on Image and Feature Data
This example shows how to train a network that classifies handwritten digits using both image and feature input data.

Deep Learning avec MATLAB

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.
Speed Up Deep Neural Network Training
Learn how to accelerate deep neural network training.
Data Sets for Deep Learning
Discover data sets for various deep learning tasks.

Exemples présentés

Prévision de séries temporelles avec le Deep Learning

Cet exemple montre comment prévoir des données de séries temporelles avec un réseau LSTM (long short-term memory).

Ouvrir le live script

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.

Ouvrir le live script

Chemical Process Fault Detection Using Deep Learning

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

Ouvrir le live script