Main Content

Cette page s'applique à la version précédente. La page correspondante en anglais a été supprimée de la version actuelle.

Deep Learning Toolbox Fonctions - Liste alphabétique

AcceleratedFunctionAccelerated deep learning function (depuis R2021a)
activationsCompute deep learning network layer activations
adamupdateUpdate parameters using adaptive moment estimation (Adam) (depuis R2019b)
adaptAdapt neural network to data as it is simulated
adaptwbAdapt network with weight and bias learning rules
adddelayAdd delay to neural network response
addInputLayerAdd input layer to network (depuis R2022b)
additionLayerAddition layer
addLayersAdd layers to layer graph or network
addMetricsCompute additional classification performance metrics (depuis R2022b)
addParameterAdd parameter to ONNXParameters object (depuis R2020b)
alexnetAlexNet convolutional neural network
analyzeNetworkAnalyze deep learning network architecture
assembleNetworkAssemble deep learning network from pretrained layers
attentionDot-product attention (depuis R2022b)
audioDataAugmenterAugment audio data (depuis R2019b)
audioDatastoreDatastore for collection of audio files
audioFeatureExtractorStreamline audio feature extraction (depuis R2019b)
augmentApply identical random transformations to multiple images
augmentedImageDatastoreTransform batches to augment image data
augmentedImageSource(To be removed) Generate batches of augmented image data
AutoencoderAutoencoder class
averageCompute performance metrics for average receiver operating characteristic (ROC) curve in multiclass problem (depuis R2022b)
averagePooling1dLayer1-D average pooling layer (depuis R2021b)
averagePooling2dLayerAverage pooling layer
averagePooling3dLayer3-D average pooling layer (depuis R2019a)
avgpoolPool data to average values over spatial dimensions (depuis R2019b)
batchnormNormalize data across all observations for each channel independently (depuis R2019b)
batchNormalizationLayerBatch normalization layer
bilstmLayerBidirectional long short-term memory (BiLSTM) layer for recurrent neural network (RNN)
blockedImageDatastoreDatastore for use with blocks from blockedImage objects (depuis R2021a)
boxdistDistance between two position vectors
boxLabelDatastoreDatastore for bounding box label data (depuis R2019b)
bttderivBackpropagation through time derivative function
calibrateSimulate and collect ranges of a deep neural network (depuis R2020a)
cascadeforwardnetGenerate cascade-forward neural network
catelementsConcatenate neural network data elements
catsamplesConcatenate neural network data samples
catsignalsConcatenate neural network data signals
cattimestepsConcatenate neural network data timesteps
cellmatCréer un cell array de matrices
checkLayerCheck validity of custom or function layer
classificationLayerClassification output layer
ClassificationOutputLayerClassification layer
classifyClassify data using trained deep learning neural network
classifyAndUpdateStateClassify data using a trained recurrent neural network and update the network state
classifySoundClassify sounds in audio signal (depuis R2020b)
clearCacheClear accelerated deep learning function trace cache (depuis R2021a)
clippedReluLayerClipped Rectified Linear Unit (ReLU) layer
closeloopConvert neural network open-loop feedback to closed loop
codegenGenerate C/C++ code from MATLAB code
coder.DeepLearningConfigCreate deep learning code generation configuration objects
coder.getDeepLearningLayersGet the list of layers supported for code generation for a specific deep learning library
coder.loadDeepLearningNetworkLoad deep learning network model
combvecCréer toutes les combinaisons de vecteurs
competCompetitive transfer function
competlayerCompetitive layer
compressNetworkUsingProjectionCompress neural network using projection (depuis R2022b)
con2seqConvert concurrent vectors to sequential vectors
concatenationLayerConcatenation layer (depuis R2019a)
concurCreate concurrent bias vectors
configureConfigure network inputs and outputs to best match input and target data
confusionMatrice de confusion pour la classification
confusionchartCreate confusion matrix chart for classification problem
confusionmatCompute confusion matrix for classification problem
connectLayersConnect layers in layer graph or network
convolution1dLayer1-D convolutional layer (depuis R2021b)
convolution2dLayer2-D convolutional layer
convolution3dLayer3-D convolutional layer (depuis R2019a)
convwfConvolution weight function
countlabelsCount number of unique labels (depuis R2021a)
crepeCREPE neural network (depuis R2021a)
crepePostprocessPostprocess output of CREPE deep learning network (depuis R2021a)
crepePreprocessPreprocess audio for CREPE deep learning network (depuis R2021a)
crop2dLayer2-D crop layer
crop3dLayer3-D crop layer (depuis R2019b)
crosschannelnormCross channel square-normalize using local responses (depuis R2020a)
crossChannelNormalizationLayer Channel-wise local response normalization layer
crossentropyCross-entropy loss for classification tasks (depuis R2019b)
crossentropyNeural network performance
ctcConnectionist temporal classification (CTC) loss for unaligned sequence classification (depuis R2021a)
cwtContinuous 1-D wavelet transform
cwtLayerContinuous wavelet transform (CWT) layer (depuis R2022b)
DAGNetworkDirected acyclic graph (DAG) network for deep learning
darknet19DarkNet-19 convolutional neural network (depuis R2020a)
darknet53DarkNet-53 convolutional neural network (depuis R2020a)
decodeDecode encoded data
deepDreamImageVisualize network features using deep dream
deeplabv3plusLayersCreate DeepLab v3+ convolutional neural network for semantic image segmentation (depuis R2019b)
defaultderivDefault derivative function
densenet201DenseNet-201 convolutional neural network
depthConcatenationLayerDepth concatenation layer
detectDetect objects using PointPillars object detector (depuis R2021b)
detectTextCRAFTDetect texts in images by using CRAFT deep learning model (depuis R2022a)
dimsÉtiquettes des dimensions de dlarray (depuis R2019b)
disconnectLayersDisconnect layers in layer graph or network
distFonction de pondération de la distance euclidienne
distdelaynetDistributed delay network
divideblockDivide targets into three sets using blocks of indices
divideindDivide targets into three sets using specified indices
divideintDivide targets into three sets using interleaved indices
dividerandDiviser des cibles en trois jeux avec des indices aléatoires
dividetrainAssign all targets to training set
dlaccelerateAccelerate deep learning function for custom training loops (depuis R2021a)
dlarrayDeep learning array for customization (depuis R2019b)
dlconvDeep learning convolution (depuis R2019b)
dlcwtDeep learning continuous wavelet transform (depuis R2022b)
dlfevalEvaluate deep learning model for custom training loops (depuis R2019b)
dlgradientCompute gradients for custom training loops using automatic differentiation (depuis R2019b)
dlhdl.TargetConfigure interface to target board for workflow deployment (depuis R2020b)
dlhdl.WorkflowConfigure deployment workflow for deep learning neural network (depuis R2020b)
dlmodwtDeep learning maximal overlap discrete wavelet transform and multiresolution analysis (depuis R2022a)
dlmtimes(Not recommended) Batch matrix multiplication for deep learning (depuis R2020a)
dlnetworkDeep learning network for custom training loops (depuis R2019b)
dlode45Deep learning solution of nonstiff ordinary differential equation (ODE) (depuis R2021b)
dlquantizationOptionsOptions for quantizing a trained deep neural network (depuis R2020a)
dlquantizerQuantize a deep neural network to 8-bit scaled integer data types (depuis R2020a)
dlstftDeep learning short-time Fourier transform (depuis R2021a)
dltranspconvDeep learning transposed convolution (depuis R2019b)
dlupdate Update parameters using custom function (depuis R2019b)
doc2sequenceConvert documents to sequences for deep learning
dotprodDot product weight function
dropoutLayerDropout layer
edfheaderCreate header structure for EDF or EDF+ file (depuis R2021a)
edfinfoGet information about EDF/EDF+ file (depuis R2020b)
edfreadRead data from EDF/EDF+ file (depuis R2020b)
edfwriteCreate or modify EDF or EDF+ file (depuis R2021a)
efficientnetb0EfficientNet-b0 convolutional neural network (depuis R2020b)
elliot2sigElliot 2 symmetric sigmoid transfer function
elliotsigElliot symmetric sigmoid transfer function
elmannetElman neural network
eluLayerExponential linear unit (ELU) layer (depuis R2019a)
embedEmbed discrete data (depuis R2020b)
encodeEncode input data
equalizeLayersEqualize layer parameters of deep neural network (depuis R2022b)
errsurfError surface of single-input neuron
estimateNetworkMetricsEstimate network metrics for specific layers of a neural network (depuis R2022a)
estimateNetworkOutputBounds Estimate output bounds of deep learning network (depuis R2022b)
experiments.MonitorUpdate results table and training plots for custom training experiments (depuis R2021a)
exportNetworkToTensorFlowExport Deep Learning Toolbox network or layer graph to TensorFlow (depuis R2022b)
exportONNXNetworkExport network to ONNX model format
extendtsExtend time series data to given number of timesteps
extractdataExtract data from dlarray (depuis R2019b)
fasterRCNNObjectDetectorDetect objects using Faster R-CNN deep learning detector
fastRCNNObjectDetectorDetect objects using Fast R-CNN deep learning detector
fastTextWordEmbeddingPretrained fastText word embedding
fcddAnomalyDetectorDetect anomalies using fully convolutional data description (FCDD) network for anomaly detection (depuis R2022b)
featureInputLayerFeature input layer (depuis R2020b)
feedforwardnetGénérer un réseau de neurones feedforward
filenames2labelsGet list of labels from filenames (depuis R2022b)
finddimFind dimensions with specified label (depuis R2019b)
findPlaceholderLayersFind placeholder layers in network architecture imported from Keras or ONNX
fitnetRéseau de neurones pour l'ajustement de fonction
fixunknownsProcess data by marking rows with unknown values
flattenLayerFlatten layer (depuis R2019a)
folders2labelsGet list of labels from folder names (depuis R2021a)
formwbForm bias and weights into single vector
forwardCompute deep learning network output for training (depuis R2019b)
fpderivForward propagation derivative function
freezeParametersConvert learnable network parameters in ONNXParameters to nonlearnable (depuis R2020b)
fromnndataConvert data from standard neural network cell array form
fullyconnectSum all weighted input data and apply a bias (depuis R2019b)
fullyConnectedLayerFully connected layer
functionLayerFunction layer (depuis R2021b)
functionToLayerGraph(To be removed) Convert deep learning model function to a layer graph (depuis R2019b)
gaddGeneralized addition
gdivideGeneralized division
geluApply Gaussian error linear unit (GELU) activation (depuis R2022b)
geluLayerGaussian error linear unit (GELU) layer (depuis R2022b)
generateFunctionGenerate a MATLAB function to run the autoencoder
generateSimulinkGenerate a Simulink model for the autoencoder
genFunctionGenerate MATLAB function for simulating shallow neural network
gensimGenerate Simulink block for shallow neural network simulation
getelementsGet neural network data elements
getL2FactorGet L2 regularization factor of layer learnable parameter
getLearnRateFactorGet learn rate factor of layer learnable parameter
getsamplesGet neural network data samples
getsignalsGet neural network data signals
getsiminitGet Simulink neural network block initial input and layer delays states
gettimestepsGet neural network data timesteps
getwbGet network weight and bias values as single vector
globalAveragePooling1dLayer1-D global average pooling layer (depuis R2021b)
globalAveragePooling2dLayer2-D global average pooling layer (depuis R2019b)
globalAveragePooling3dLayer3-D global average pooling layer (depuis R2019b)
globalMaxPooling1dLayer1-D global max pooling layer (depuis R2021b)
globalMaxPooling2dLayerGlobal max pooling layer (depuis R2020a)
globalMaxPooling3dLayer3-D global max pooling layer (depuis R2020a)
gmultiplyGeneralized multiplication
gnegateGeneralized negation
googlenetRéseau de neurones à convolution GoogLeNet
gpu2nndataReformat neural data back from GPU
gradCAMExplain network predictions using Grad-CAM (depuis R2021a)
gridtopGrid layer topology function
groupedConvolution2dLayer2-D grouped convolutional layer (depuis R2019a)
groupnormNormalize data across grouped subsets of channels for each observation independently (depuis R2020b)
groupNormalizationLayerGroup normalization layer (depuis R2020b)
groupSubPlotGroup metrics in experiment training plot (depuis R2021a)
groupSubPlotGroup metrics in training plot (depuis R2022b)
gruGated recurrent unit (depuis R2020a)
gruLayerGated recurrent unit (GRU) layer for recurrent neural network (RNN) (depuis R2020a)
gsqrtGeneralized square root
gsubtractSoustraction généralisée
hardlimHard-limit transfer function
hardlimsSymmetric hard-limit transfer function
hasdataDetermine if minibatchqueue can return mini-batch (depuis R2020b)
hextopHexagonal layer topology function
huberHuber loss for regression tasks (depuis R2021a)
image3dInputLayer3-D image input layer (depuis R2019a)
imageDataAugmenterConfigure image data augmentation
imageInputLayerImage input layer
imageLIMEExplain network predictions using LIME (depuis R2020b)
importCaffeLayersImport convolutional neural network layers from Caffe
importCaffeNetworkImport pretrained convolutional neural network models from Caffe
importKerasLayers(To be removed) Import layers from Keras network
importKerasNetwork(To be removed) Import pretrained Keras network and weights
importNetworkFromPyTorchImport PyTorch network as MATLAB network (depuis R2022b)
importONNXFunctionImport pretrained ONNX network as a function (depuis R2020b)
importONNXLayers(To be removed) Import layers from ONNX network
importONNXNetwork(To be removed) Import pretrained ONNX network
importTensorFlowLayers(To be removed) Import layers from TensorFlow network (depuis R2021a)
importTensorFlowNetwork(To be removed) Import pretrained TensorFlow network (depuis R2021a)
inceptionresnetv2Pretrained Inception-ResNet-v2 convolutional neural network
inceptionv3Inception-v3 convolutional neural network
ind2vecConvert indices to vectors
ind2wordMap encoding index to word
initInitialize neural network
initconConscience bias initialization function
initializeInitialize learnable and state parameters of a dlnetwork (depuis R2021a)
initlayLayer-by-layer network initialization function
initlvqLVQ weight initialization function
initnwNguyen-Widrow layer initialization function
initwbBy weight and bias layer initialization function
initzeroZero weight and bias initialization function
instancenormNormalize across each channel for each observation independently (depuis R2021a)
instanceNormalizationLayerInstance normalization layer (depuis R2021a)
isconfiguredIndicate if network inputs and outputs are configured
isdlarrayCheck if object is dlarray (depuis R2020b)
isequalCheck equality of deep learning layer graphs or networks (depuis R2021a)
isequalnCheck equality of deep learning layer graphs or networks ignoring NaN values (depuis R2021a)
isVocabularyWordTest if word is member of word embedding or encoding
l1lossL1 loss for regression tasks (depuis R2021b)
l2lossL2 loss for regression tasks (depuis R2021b)
labeledSignalSetCreate labeled signal set
LayerNetwork layer for deep learning
layerGraphGraph of network layers for deep learning
layernormNormalize data across all channels for each observation independently (depuis R2021a)
layerNormalizationLayerLayer normalization layer (depuis R2021a)
layrecnetLayer recurrent neural network
leakyreluApply leaky rectified linear unit activation (depuis R2019b)
leakyReluLayerLeaky Rectified Linear Unit (ReLU) layer
learnconConscience bias learning function
learngdGradient descent weight and bias learning function
learngdmGradient descent with momentum weight and bias learning function
learnhHebb weight learning rule
learnhdHebb with decay weight learning rule
learnisInstar weight learning function
learnkKohonen weight learning function
learnlv1LVQ1 weight learning function
learnlv2LVQ2.1 weight learning function
learnosOutstar weight learning function
learnpPerceptron weight and bias learning function
learnpnNormalized perceptron weight and bias learning function
learnsomSelf-organizing map weight learning function
learnsombBatch self-organizing map weight learning function
learnwhWidrow-Hoff weight/bias learning function
linearlayerCreate linear layer
linkdistLink distance function
loadTFLiteModelLoad TensorFlow Lite model (depuis R2022a)
logsigLog-sigmoid transfer function
lstmLong short-term memory (depuis R2019b)
lstmLayerLong short-term memory (LSTM) layer for recurrent neural network (RNN)
lstmProjectedLayerLong short-term memory (LSTM) projected layer for recurrent neural network (RNN) (depuis R2022b)
lvqnetLearning vector quantization neural network
lvqoutputsLVQ outputs processing function
maeMean absolute error performance function
mandistManhattan distance weight function
mapminmaxTransformer des matrices en mappant des valeurs de ligne minimales et maximales sur [-1 1]
mapstdProcess matrices by mapping each row’s means to 0 and deviations to 1
maskrcnnDetect objects using Mask R-CNN instance segmentation (depuis R2021b)
matlab.io.datastore.BackgroundDispatchable(Not recommended) Add prefetch reading support to datastore
matlab.io.datastore.BackgroundDispatchable.readByIndex(Not recommended) Return observations specified by index from datastore
matlab.io.datastore.MiniBatchableAdd mini-batch support to datastore
matlab.io.datastore.MiniBatchable.read(Not recommended) Read data from custom mini-batch datastore
matlab.io.datastore.PartitionableByIndex(Not recommended) Add parallelization support to datastore
matlab.io.datastore.PartitionableByIndex.partitionByIndex(Not recommended) Partition datastore according to indices
maxlinlrMaximum learning rate for linear layer
maxpoolPool data to maximum value (depuis R2019b)
maxPooling1dLayer1-D max pooling layer (depuis R2021b)
maxPooling2dLayerMax pooling layer
maxPooling3dLayer3-D max pooling layer (depuis R2019a)
maxunpoolUnpool the output of a maximum pooling operation (depuis R2019b)
maxUnpooling2dLayerMax unpooling layer
meanabsMean of absolute elements of matrix or matrices
meansqrMean of squared elements of matrix or matrices
midpointMidpoint weight initialization function
minibatchqueueCreate mini-batches for deep learning (depuis R2020b)
minmaxPlages des lignes d'une matrice
mobilenetv2MobileNet-v2 convolutional neural network (depuis R2019a)
modwtMaximal overlap discrete wavelet transform
modwtLayerMaximal overlap discrete wavelet transform (MODWT) layer (depuis R2022b)
mseHalf mean squared error (depuis R2019b)
mseFonction de performance d’erreur quadratique moyenne normalisée
multiplicationLayerMultiplication layer (depuis R2020b)
narnetNonlinear autoregressive neural network
narxnetNonlinear autoregressive neural network with external input
nasnetlargePretrained NASNet-Large convolutional neural network (depuis R2019a)
nasnetmobilePretrained NASNet-Mobile convolutional neural network (depuis R2019a)
nctoolOpen Neural Net Clustering app
negdistNegative distance weight function
netinvInverse transfer function
netprodProduct net input function
netsumSum net input function
networkConvert Autoencoder object into network object
networkCréer un réseau de neurones peu profond personnalisé
networkDataLayoutDeep learning network data layout for learnable parameter initialization (depuis R2022b)
neuronPCAPrincipal component analysis of neuron activations (depuis R2022b)
newgrnnDesign generalized regression neural network
newlindDesign linear layer
newpnnDesign probabilistic neural network
newrbDesign radial basis network
newrbeDesign exact radial basis network
nextObtain next mini-batch of data from minibatchqueue (depuis R2020b)
nftoolOuvrir l’application Neural Net Fitting
nncell2matCombine neural network cell data into matrix
nncorrCross correlation between neural network time series
nndataCreate neural network data
nndata2gpuFormat neural data for efficient GPU training or simulation
nndata2simConvert neural network data to Simulink time series
nnsizeNumber of neural data elements, samples, timesteps, and signals
nntool(Supprimé) Ouvrir Network/Data Manager
nntraintool(Removed) Neural network training tool
noloopRemove neural network open- and closed-loop feedback
normcNormaliser des colonnes de matrice
normprodNormalized dot product weight function
normrNormalize rows of matrix
nprtoolOuvrir l’application Neural Net Pattern Recognition
ntstoolOuvrir l’application Neural Net Time Series
num2derivNumeric two-point network derivative function
num5derivNumeric five-point stencil neural network derivative function
numelementsNumber of elements in neural network data
numfiniteNumber of finite values in neural network data
numnanNumber of NaN values in neural network data
numsamplesNumber of samples in neural network data
numsignalsNumber of signals in neural network data
numtimestepsNumber of time steps in neural network data
occlusionSensitivityExplain network predictions by occluding the inputs (depuis R2019b)
onehotdecodeDecode probability vectors into class labels (depuis R2020b)
onehotencodeEncode data labels into one-hot vectors (depuis R2020b)
ONNXParametersParameters of imported ONNX network for deep learning (depuis R2020b)
openl3OpenL3 neural network (depuis R2021a)
openl3EmbeddingsExtract OpenL3 feature embeddings (depuis R2022a)
openl3PreprocessPreprocess audio for OpenL3 feature extraction (depuis R2021a)
openloopConvert neural network closed-loop feedback to open loop
padsequencesPad or truncate sequence data to same length (depuis R2021a)
partitionPartition minibatchqueue (depuis R2020b)
partitionByIndexPartition augmentedImageDatastore according to indices
patternnetGénérer un réseau de reconnaissance de formes
perceptronClassifieur binaire simple à couche unique
performCalculate network performance
pitchnnEstimate pitch with deep learning neural network (depuis R2021a)
pixelLabelDatastoreDatastore for pixel label data
PlaceholderLayerLayer replacing an unsupported Keras or ONNX layer
plotPlot neural network architecture
plotPlot receiver operating characteristic (ROC) curves and other performance curves (depuis R2022b)
plotconfusionPlot classification confusion matrix
plotepPlot weight-bias position on error surface
ploterrcorrPlot autocorrelation of error time series
ploterrhistPlot error histogram
plotesPlot error surface of single-input neuron
plotfitTracer l'approximation d'une fonction
plotinerrcorrPlot input to error time-series cross-correlation
plotpcPlot classification line on perceptron vector plot
plotperformTracer les performances d’un réseau
plotpvTracer les vecteurs d’entrée/cibles d'un perceptron
plotregressionTracer une régression linéaire
plotresponsePlot dynamic network time series response
plotrocTracer la fonction d’efficacité d’un récepteur
plotsomPlot self-organizing map
plotsomhitsTracer les neurones vainqueurs (Sample Hits) d'une carte auto-organisatrice
plotsomncPlot self-organizing map neighbor connections
plotsomndPlot self-organizing map neighbor distances
plotsomplanesPlot self-organizing map weight planes
plotsomposPlot self-organizing map weight positions
plotsomtopPlot self-organizing map topology
plottrainstateTracer les valeurs d'un état de l’apprentissage
plotvTracer des vecteurs sous forme de lignes depuis l’origine
plotvecTracer des vecteurs avec différentes couleurs
plotwbPlot Hinton diagram of weight and bias values
plotWeightsPlot a visualization of the weights for the encoder of an autoencoder
pnormcPseudonormalize columns of matrix
pointnetplusLayersCreate PointNet++ segmentation network (depuis R2021b)
pointPillarsObjectDetectorPointPillars object detector (depuis R2021b)
poslinPositive linear transfer function
predictPredict responses using trained deep learning neural network
predictCompute deep learning network output for inference (depuis R2019b)
predictCompute deep learning network output for inference by using a TensorFlow Lite model (depuis R2022a)
predictReconstruct the inputs using trained autoencoder
predictAndUpdateStatePredict responses using a trained recurrent neural network and update the network state
preparetsPrepare input and target time series data for network simulation or training
processpcaProcess columns of matrix with principal component analysis
pruneDelete neural inputs, layers, and outputs with sizes of zero
prunedataPrune data for consistency with pruned network
purelinFonction de transfert linéaire
quantDiscrétiser des valeurs comme multiples d’une quantité
quantizationDetailsDisplay quantization details for a neural network (depuis R2022a)
quantizeQuantize deep neural network (depuis R2022a)
radbasFonction de transfert à base radiale
radbasnNormalized radial basis transfer function
randncNormalized column weight initialization function
randnrNormalized row weight initialization function
randomPatchExtractionDatastoreDatastore for extracting random 2-D or 3-D random patches from images or pixel label images
randsFonction d’initialisation aléatoire symétrique des poids/biais
randsmallSmall random weight/bias initialization function
randtopRandom layer topology function
rcnnObjectDetectorDetect objects using R-CNN deep learning detector
readRead data from augmentedImageDatastore
readByIndexRead data specified by index from augmentedImageDatastore
readWordEmbeddingRead word embedding from file
recordMetricsRecord metric values in experiment results table and training plot (depuis R2021a)
recordMetricsRecord metric values for custom training loops (depuis R2022b)
regression(Not recommended) Perform linear regression of shallow network outputs on targets
regressionLayerCouche de sortie de régression
RegressionOutputLayerRegression output layer
reluApply rectified linear unit activation (depuis R2019b)
reluLayerCouche ReLU (Rectified Linear Unit)
removeconstantrowsProcess matrices by removing rows with constant values
removedelayRemove delay to neural network’s response
removeLayersRemove layers from layer graph or network
removeParameterRemove parameter from ONNXParameters object (depuis R2020b)
removerowsProcess matrices by removing rows with specified indices
replaceLayerReplace layer in layer graph or network
resetReset minibatchqueue to start of data (depuis R2020b)
resetStateReset state parameters of neural network
resnet101ResNet-101 convolutional neural network
resnet18ResNet-18 convolutional neural network
resnet3dLayersCreate 3-D residual network (depuis R2021b)
resnet50Réseau de neurones à convolution ResNet-50
resnetLayersCreate 2-D residual network (depuis R2021b)
revertChange network weights and biases to previous initialization values
rmspropupdate Update parameters using root mean squared propagation (RMSProp) (depuis R2019b)
rocReceiver operating characteristic
rocmetricsReceiver operating characteristic (ROC) curve and performance metrics for binary and multiclass classifiers (depuis R2022b)
saeSum absolute error performance function
satlinSaturating linear transfer function
satlinsSymmetric saturating linear transfer function
scalprodScalar product weight function
segnetLayersCreate SegNet layers for semantic segmentation
selforgmapSelf-organizing map
separatewbSeparate biases and weight values from weight/bias vector
seq2conConvert sequential vectors to concurrent vectors
sequenceFoldingLayerSequence folding layer (depuis R2019a)
sequenceInputLayerSequence input layer
sequenceUnfoldingLayerSequence unfolding layer (depuis R2019a)
SeriesNetworkSeries network for deep learning
setelementsSet neural network data elements
setL2FactorSet L2 regularization factor of layer learnable parameter
setLearnRateFactorSet learn rate factor of layer learnable parameter
setsamplesSet neural network data samples
setsignalsSet neural network data signals
setsiminitSet neural network Simulink block initial conditions
settimestepsSet neural network data timesteps
setwbSet all network weight and bias values with single vector
sgdmupdate Update parameters using stochastic gradient descent with momentum (SGDM) (depuis R2019b)
shuffleShuffle data in augmentedImageDatastore
shuffleShuffle data in minibatchqueue (depuis R2020b)
shufflenetPretrained ShuffleNet convolutional neural network (depuis R2019a)
sigmoidAppliquer l’activation sigmoïde (depuis R2019b)
sigmoidLayerSigmoid layer (depuis R2020b)
signalDatastoreDatastore for collection of signals (depuis R2020a)
signalFrequencyFeatureExtractorStreamline signal frequency feature extraction (depuis R2021b)
signalLabelDefinitionCreate signal label definition
signalMaskModify and convert signal masks and extract signal regions of interest (depuis R2020b)
signalTimeFeatureExtractorStreamline signal time feature extraction (depuis R2021a)
simSimulate neural network
sim2nndataConvert Simulink time series to neural network data
softmaxApply softmax activation to channel dimension (depuis R2019b)
softmaxSoftmax transfer function
softmaxLayerCouche softmax
sortClassesSort classes of confusion matrix chart
splitlabelsFind indices to split labels according to specified proportions (depuis R2021a)
squeezenetSqueezeNet convolutional neural network
squeezesegv2LayersCreate SqueezeSegV2 segmentation network for organized lidar point cloud (depuis R2020b)
srchbac1-D minimization using backtracking
srchbre1-D interval location using Brent’s method
srchcha1-D minimization using Charalambous' method
srchgol1-D minimization using golden section search
srchhyb1-D minimization using a hybrid bisection-cubic search
ssdObjectDetectorDetect objects using SSD deep learning detector (depuis R2020a)
sseSum squared error performance function
stackStack encoders from several autoencoders together
staticderivStatic derivative function
stftShort-time Fourier transform (depuis R2019a)
stftLayerShort-time Fourier transform layer (depuis R2021b)
stripdimsRemove dlarray data format (depuis R2019b)
sumabsSomme des éléments absolus d’une ou plusieurs matrices
summaryPrint network summary (depuis R2022b)
sumsqrSomme d’éléments au carré d’une ou plusieurs matrices
swishLayerSwish layer (depuis R2021a)
tanhLayerHyperbolic tangent (tanh) layer (depuis R2019a)
tansigFonction de transfert sigmoïde tangente hyperbolique
tapdelayShift neural network time series data for tap delay
taylorPrunableNetworkNetwork that can be pruned by using first-order Taylor approximation (depuis R2022a)
TFLiteModelTensorFlow Lite model (depuis R2022a)
timedelaynetTime delay neural network
tonndataConvert data to standard neural network cell array form
trainEntraîner un réseau de neurones peu profond
trainAutoencoderTrain an autoencoder
trainbBatch training with weight and bias learning rules
trainbfgBFGS quasi-Newton backpropagation
trainbrBayesian regularization backpropagation
trainbuBatch unsupervised weight/bias training
traincCyclical order weight/bias training
traincgbConjugate gradient backpropagation with Powell-Beale restarts
traincgfConjugate gradient backpropagation with Fletcher-Reeves updates
traincgpConjugate gradient backpropagation with Polak-Ribiére updates
traingdGradient descent backpropagation
traingdaGradient descent with adaptive learning rate backpropagation
traingdmGradient descent with momentum backpropagation
traingdxGradient descent with momentum and adaptive learning rate backpropagation
trainingOptionsOptions d’un réseau de neurones d’apprentissage pour le Deep Learning
TrainingOptionsADAMTraining options for Adam optimizer
TrainingOptionsRMSPropTraining options for RMSProp optimizer
TrainingOptionsSGDMTraining options for stochastic gradient descent with momentum
trainingProgressMonitorMonitor and plot training progress for deep learning custom training loops (depuis R2022b)
trainlmLevenberg-Marquardt backpropagation
trainNetworkTrain neural network
trainossOne-step secant backpropagation
trainPointPillarsObjectDetectorTrain PointPillars object detector (depuis R2021b)
trainrRandom order incremental training with learning functions
trainrpResilient backpropagation
trainruUnsupervised random order weight/bias training
trainsSequential order incremental training with learning functions
trainscgScaled conjugate gradient backpropagation
trainSoftmaxLayerTrain a softmax layer for classification
trainWordEmbeddingTrain word embedding
transposedConv1dLayerTransposed 1-D convolution layer (depuis R2022a)
transposedConv2dLayerTransposed 2-D convolution layer
transposedConv3dLayerTransposed 3-D convolution layer (depuis R2019a)
TransposedConvolution1DLayerTransposed 1-D convolution layer (depuis R2022a)
TransposedConvolution2DLayerTransposed 2-D convolution layer
TransposedConvolution3dLayerTransposed 3-D convolution layer (depuis R2019a)
tribasTriangular basis transfer function
tritopTriangle layer topology function
unconfigureUnconfigure network inputs and outputs
unet3dLayersCreate 3-D U-Net layers for semantic segmentation of volumetric images (depuis R2019b)
unetLayersCreate U-Net layers for semantic segmentation
unfreezeParametersConvert nonlearnable network parameters in ONNXParameters to learnable (depuis R2020b)
updateInfoUpdate information columns in experiment results table (depuis R2021a)
updateInfoUpdate information values for custom training loops (depuis R2022b)
updatePrunablesRemove filters from prunable layers based on importance scores (depuis R2022a)
updateScoreCompute and accumulate Taylor-based importance scores for pruning (depuis R2022a)
validateQuantize and validate a deep neural network (depuis R2020a)
vec2indConvert vectors to indices
vec2wordMap embedding vector to word
verifyNetworkRobustnessVerify adversarial robustness of deep learning network (depuis R2022b)
vgg16VGG-16 convolutional neural network
vgg19VGG-19 convolutional neural network
vggishVGGish neural network (depuis R2020b)
vggishEmbeddingsExtract VGGish feature embeddings (depuis R2022a)
vggishPreprocessPreprocess audio for VGGish feature extraction (depuis R2021a)
viewAfficher un réseau de neurones peu profond
viewView autoencoder
waveletScatteringWavelet time scattering
word2indMap word to encoding index
word2vecMap word to embedding vector
wordEmbeddingWord embedding model to map words to vectors and back
wordEmbeddingLayerWord embedding layer for deep learning neural network
wordEncodingWord encoding model to map words to indices and back
writeWordEmbeddingWrite word embedding file
xceptionXception convolutional neural network (depuis R2019a)
yamnetYAMNet neural network (depuis R2020b)
yamnetGraphGraph of YAMNet AudioSet ontology (depuis R2020b)
yamnetPreprocessPreprocess audio for YAMNet classification (depuis R2021a)
yolov2ObjectDetectorDetect objects using YOLO v2 object detector (depuis R2019a)
yolov3ObjectDetectorDetect objects using YOLO v3 object detector (depuis R2021a)
yolov4ObjectDetectorDetect objects using YOLO v4 object detector (depuis R2022a)