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

Deep Learning avec des données de séries temporelles et de séquences

Créer et entraîner des réseaux pour des tâches de classification, de régression et de prévision de séries temporelles

Créer et entraîner des réseaux pour des tâches de classification, de régression et de prévision de séries temporelles. Entraînez des réseaux LSTM (Long Short-Term Memory) pour des problèmes de classification et de régression sequence-to-one et sequence-to-label. Vous pouvez entraîner des réseaux LSTM sur des données texte avec des couches de word embedding (vectorisation de mots) nécessitant Text Analytics Toolbox™ ou des réseaux de neurones à convolution sur des données audio avec des spectrogrammes nécessitant Audio Toolbox™.

Applications

Deep Network Designer

Concevoir, visualiser et entraîner des réseaux de Deep Learning

Fonctions

développer tout

Entraîner le réseau

`trainingOptions`	Options d’un réseau de neurones d’apprentissage pour le Deep Learning
`trainNetwork`	(Not recommended) Train neural network
`analyzeNetwork`	Analyze deep learning network architecture

Couches

Couches d’entrée

`sequenceInputLayer`	Sequence input layer
`featureInputLayer`	Feature input layer (depuis R2020b)

Couches récurrentes

`lstmLayer`	Long short-term memory (LSTM) layer for recurrent neural network (RNN)
`bilstmLayer`	Bidirectional long short-term memory (BiLSTM) layer for recurrent neural network (RNN)
`gruLayer`	Gated recurrent unit (GRU) layer for recurrent neural network (RNN) (depuis R2020a)
`lstmProjectedLayer`	Long short-term memory (LSTM) projected layer for recurrent neural network (RNN) (depuis R2022b)

Couches de convolution et couches entièrement connectées

`convolution1dLayer`	1-D convolutional layer (depuis R2021b)
`transposedConv1dLayer`	Transposed 1-D convolution layer (depuis R2022a)
`fullyConnectedLayer`	Fully connected layer

Couches de pooling

`maxPooling1dLayer`	1-D max pooling layer (depuis R2021b)
`averagePooling1dLayer`	1-D average pooling layer (depuis R2021b)
`globalMaxPooling1dLayer`	1-D global max pooling layer (depuis R2021b)
`globalAveragePooling1dLayer`	1-D global average pooling layer (depuis R2021b)

Couches d’activation et de dropout

`reluLayer`	Couche ReLU (Rectified Linear Unit)
`leakyReluLayer`	Leaky Rectified Linear Unit (ReLU) layer
`clippedReluLayer`	Clipped Rectified Linear Unit (ReLU) layer
`eluLayer`	Exponential linear unit (ELU) layer
`tanhLayer`	Hyperbolic tangent (tanh) layer
`swishLayer`	Swish layer (depuis R2021a)
`geluLayer`	Gaussian error linear unit (GELU) layer (depuis R2022b)
`softmaxLayer`	Couche softmax
`dropoutLayer`	Dropout layer
`functionLayer`	Function layer (depuis R2021b)

Manipulation de données

`sequenceFoldingLayer`	(Not recommended) Sequence folding layer
`sequenceUnfoldingLayer`	(Not recommended) Sequence unfolding layer
`flattenLayer`	Flatten layer

Couches de sortie

`classificationLayer`	(Not recommended) Classification output layer
`regressionLayer`	Couche de sortie de régression

Prédiction

`classify`	(Not recommended) Classify data using trained deep learning neural network
`predict`	(Not recommended) Predict responses using trained deep learning neural network
`activations`	(Not recommended) Compute deep learning network layer activations
`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
`confusionchart`	Create confusion matrix chart for classification problem
`sortClasses`	Sort classes of confusion matrix chart

Boucles d’apprentissage personnalisées

padsequences Pad or truncate sequence data to same length (depuis R2021a)

Blocs

développer tout

Réseaux de neurones profonds

Predict	Predict responses using a trained deep learning neural network (depuis R2020b)
Stateful Predict	Predict responses using a trained recurrent neural network (depuis R2021a)
Stateful Classify	Classify data using a trained deep learning recurrent neural network (depuis R2021a)

Propriétés

ConfusionMatrixChart Properties

Confusion matrix chart appearance and behavior

Rubriques

Réseaux récurrents

Long Short-Term Memory Neural Networks
Learn about long short-term memory (LSTM) neural networks.
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).
Classification de séquences avec le Deep Learning
Cet exemple montre comment classer des données séquentielles avec un réseau LSTM (long short-term memory).
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.
Utiliser Deep Network Designer pour créer un réseau simple de classification de séquences
Cet exemple montre comment utiliser Deep Network Designer pour créer un réseau LSTM (long short-term memory) simple.
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.
Classify Videos Using Deep Learning with Custom Training Loop
This example shows how to create a network for video classification by combining a pretrained image classification model and a sequence classification network.
Image Captioning Using Attention
This example shows how to train a deep learning model for image captioning using attention.
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.
Visualize Activations of LSTM Network
This example shows how to investigate and visualize the features learned by LSTM networks by extracting the activations.
Chemical Process Fault Detection Using Deep Learning
Use simulation data to train a neural network than can detect faults in a chemical process.
Utiliser Deep Network Designer pour créer un réseau simple de classification de séquences
Cet exemple montre comment utiliser Deep Network Designer pour créer un réseau LSTM (long short-term memory) simple.
Train Latent ODE Network with Irregularly Sampled Time-Series Data
This example shows how to train a latent ordinary differential equation (ODE) autoencoder with time-series data that is sampled at irregular time intervals.

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 Speech Command Recognition Model Using Deep Learning
This example shows how to train a deep learning model that detects the presence of speech commands in audio.
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.
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.
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 with Numeric Features
This example shows how to create and train a simple neural network for deep learning feature data classification.

Deep Learning avec Simulink

Predict and Update Network State in Simulink
This example shows how to predict responses for a trained recurrent neural network in Simulink® by using the Stateful Predict block.
Classify and Update Network State in Simulink
This example shows how to classify data for a trained recurrent neural network in Simulink® by using the Stateful Classify block.
Predict Battery State of Charge Using Deep Learning
This example shows how to train a neural network to predict the state of charge of a battery by using deep learning.
Improve Performance of Deep Learning Simulations in Simulink
This example shows how to use code generation to improve the performance of deep learning simulations in Simulink®.
Physical System Modeling Using LSTM Network in Simulink
This example shows how to create a reduced order model (ROM) to replace a Simscape component in a Simulink® model by training a long short-term memory (LSTM) neural network.

Deep Learning avec MATLAB

List of Deep Learning Layers
Discover all the deep learning layers in MATLAB^®.
Datastores for Deep Learning
Learn how to use datastores in deep learning applications.
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.
Data Sets for Deep Learning
Discover data sets for various deep learning tasks.

Exemples présentés

Classification de séquences avec le Deep Learning

Cet exemple montre comment classer des données séquentielles avec un réseau LSTM (long short-term memory).

Ouvrir le live script

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