Main Content

Deep Learning with Time Series and Sequence Data

Create and train networks for time series classification, regression, and forecasting tasks

Create and train networks for time series classification, regression, and forecasting tasks. Train long short-term memory (LSTM) networks for sequence-to-one or sequence-to-label classification and regression problems. You can train LSTM networks on text data using word embedding layers (requires Text Analytics Toolbox™) or convolutional neural networks on audio data using spectrograms (requires Audio Toolbox™).

Apps

Deep Network DesignerDesign, visualize, and train deep learning networks

Functions

expand all

trainingOptionsOptions for training deep learning neural network
trainNetworkTrain deep learning neural network
analyzeNetworkAnalyze deep learning network architecture

Input Layers

sequenceInputLayerSequence input layer
featureInputLayerFeature input layer

Recurrent Layers

lstmLayerLong short-term memory (LSTM) layer
bilstmLayerBidirectional long short-term memory (BiLSTM) layer
gruLayerGated recurrent unit (GRU) layer

Convolution and Fully Connected Layers

convolution1dLayer1-D convolutional layer
transposedConv1dLayerTransposed 1-D convolution layer
fullyConnectedLayerFully connected layer

Pooling Layers

maxPooling1dLayer1-D max pooling layer
averagePooling1dLayer1-D average pooling layer
globalMaxPooling1dLayer1-D global max pooling layer
globalAveragePooling1dLayer1-D global average pooling layer

Activation and Dropout Layers

reluLayerRectified Linear Unit (ReLU) layer
leakyReluLayerLeaky Rectified Linear Unit (ReLU) layer
clippedReluLayerClipped Rectified Linear Unit (ReLU) layer
eluLayerExponential linear unit (ELU) layer
tanhLayerHyperbolic tangent (tanh) layer
swishLayerSwish layer
softmaxLayerSoftmax layer
dropoutLayerDropout layer
functionLayerFunction layer

Data Manipulation

sequenceFoldingLayerSequence folding layer
sequenceUnfoldingLayerSequence unfolding layer
flattenLayerFlatten layer

Output Layers

classificationLayerClassification output layer
regressionLayerCreate a regression output layer
classifyClassify data using trained deep learning neural network
predictPredict responses using trained deep learning neural network
activationsCompute deep learning network layer activations
predictAndUpdateStatePredict responses using a trained recurrent neural network and update the network state
classifyAndUpdateStateClassify data using a trained recurrent neural network and update the network state
resetStateReset state parameters of neural network
confusionchartCreate confusion matrix chart for classification problem
sortClassesSort classes of confusion matrix chart
padsequencesPad or truncate sequence data to same length

Blocks

expand all

PredictPredict responses using a trained deep learning neural network
Stateful PredictPredict responses using a trained recurrent neural network
Stateful ClassifyClassify data using a trained deep learning recurrent neural network

Properties

ConfusionMatrixChart PropertiesConfusion matrix chart appearance and behavior

Examples and How To

Sequences and Time Series

Concepts