Main Content

本页面提供的是上一版软件的文档。当前版本中已删除对应的英文页面。

Deep Learning Toolbox 函数 - 按字母顺序排列的列表

AcceleratedFunctionAccelerated deep learning function (自 R2021a 起)
accuracyMetricDeep learning accuracy metric (自 R2023b 起)
activations计算深度学习网络层激活
adamupdateUpdate parameters using adaptive moment estimation (Adam) (自 R2019b 起)
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 (自 R2022b 起)
additionLayerAddition layer
addLayersAdd layers to layer graph or network
addMetricsCompute additional classification performance metrics (自 R2022b 起)
addParameterAdd parameter to ONNXParameters object (自 R2020b 起)
alexnetAlexNet 卷积神经网络
analyzeNetworkAnalyze deep learning network architecture
assembleNetworkAssemble deep learning network from pretrained layers
attentionDot-product attention (自 R2022b 起)
aucMetricDeep learning area under ROC curve (AUC) metric (自 R2023b 起)
audioDataAugmenterAugment audio data (自 R2019b 起)
audioDatastoreDatastore for collection of audio files
audioFeatureExtractorStreamline audio feature extraction (自 R2019b 起)
augmentApply identical random transformations to multiple images
augmentedImageDatastore变换批量以增强图像数据
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 (自 R2022b 起)
averagePooling1dLayer1-D average pooling layer (自 R2021b 起)
averagePooling2dLayerAverage pooling layer
averagePooling3dLayer3-D average pooling layer (自 R2019a 起)
avgpoolPool data to average values over spatial dimensions (自 R2019b 起)
BaselineDistributionDiscriminatorBaseline distribution discriminator (自 R2023a 起)
batchnormNormalize data across all observations for each channel independently (自 R2019b 起)
batchNormalizationLayerBatch normalization layer
bilstmLayerBidirectional long short-term memory (BiLSTM) layer for recurrent neural network (RNN)
blockedImageDatastoreDatastore for use with blocks from blockedImage objects (自 R2021a 起)
boxdistDistance between two position vectors
boxLabelDatastoreDatastore for bounding box label data (自 R2019b 起)
bttderivBackpropagation through time derivative function
calibrateSimulate and collect ranges of a deep neural network (自 R2020a 起)
cascadeforwardnet生成级联前向神经网络
catelementsConcatenate neural network data elements
catsamplesConcatenate neural network data samples
catsignalsConcatenate neural network data signals
cattimestepsConcatenate neural network data timesteps
cellmat创建由矩阵组成的元胞数组
cellposeConfigure Cellpose model for cell segmentation (自 R2023b 起)
checkLayerCheck validity of custom or function layer
classificationLayer分类输出层
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 (自 R2020b 起)
clearCacheClear accelerated deep learning function trace cache (自 R2021a 起)
clippedReluLayerClipped Rectified Linear Unit (ReLU) layer
closeClose training information plot (自 R2023b 起)
closeloopConvert neural network open-loop feedback to closed loop
codegenMATLAB 代码生成 C/C++ 代码。
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
coder.loadNetworkDistributionDiscriminatorLoad network distribution discriminator for code generation (自 R2023a 起)
combine合并来自多个数据存储的数据 (自 R2019a 起)
CombinedDatastore数据存储会合并从多个基础数据存储读取的数据 (自 R2019a 起)
combvec创建向量的所有组合
competCompetitive transfer function
competlayerCompetitive layer
compressNetworkUsingProjectionCompress neural network using projection (自 R2022b 起)
con2seqConvert concurrent vectors to sequential vectors
concatenationLayerConcatenation layer (自 R2019a 起)
concurCreate concurrent bias vectors
configureConfigure network inputs and outputs to best match input and target data
confusion分类混淆矩阵
confusionchartCreate confusion matrix chart for classification problem
confusionmatCompute confusion matrix for classification problem
connectLayersConnect layers in layer graph or network
convolution1dLayer1-D convolutional layer (自 R2021b 起)
convolution2dLayer2-D convolutional layer
convolution3dLayer3-D convolutional layer (自 R2019a 起)
convwfConvolution weight function
countlabelsCount number of unique labels (自 R2021a 起)
crepeCREPE neural network (自 R2021a 起)
crop2dLayer2-D crop layer
crop3dLayer3-D crop layer (自 R2019b 起)
crosschannelnormCross channel square-normalize using local responses (自 R2020a 起)
crossChannelNormalizationLayer Channel-wise local response normalization layer
crossentropyCross-entropy loss for classification tasks (自 R2019b 起)
crossentropyNeural network performance
ctcConnectionist temporal classification (CTC) loss for unaligned sequence classification (自 R2021a 起)
cwtfilterbankContinuous wavelet transform filter bank
cwtLayerContinuous wavelet transform (CWT) layer (自 R2022b 起)
cwtmag2sigSignal reconstruction from CWT magnitude (自 R2023b 起)
DAGNetwork用于深度学习的有向无环图 (DAG) 网络
darknet19DarkNet-19 卷积神经网络 (自 R2020a 起)
darknet53DarkNet-53 卷积神经网络 (自 R2020a 起)
decodeDecode encoded data
deepDreamImageVisualize network features using deep dream
deeplabv3plusLayersCreate DeepLab v3+ convolutional neural network for semantic image segmentation (自 R2019b 起)
deepSignalAnomalyDetectorCreate signal anomaly detector (自 R2023a 起)
defaultderivDefault derivative function
densenet201DenseNet-201 卷积神经网络
depthConcatenationLayerDepth concatenation layer
detectDetect objects using PointPillars object detector (自 R2021b 起)
detectspeechnnDetect boundaries of speech in audio signal using AI (自 R2023a 起)
detectTextCRAFTDetect texts in images by using CRAFT deep learning model (自 R2022a 起)
dimsdlarray 的维度标签 (自 R2019b 起)
disconnectLayersDisconnect layers in layer graph or network
dist欧几里德距离权重函数
distdelaynetDistributed delay network
distributionScoresDistribution confidence scores (自 R2023a 起)
divideblock使用索引块将目标分为三个数据集
divideindDivide targets into three sets using specified indices
divideint使用交错索引将目标分为三组
dividerand使用随机索引将目标分为三组
dividetrain将所有目标分配给训练集
dlaccelerateAccelerate deep learning function for custom training loops (自 R2021a 起)
dlarrayDeep learning array for customization (自 R2019b 起)
dlconvDeep learning convolution (自 R2019b 起)
dlcwtDeep learning continuous wavelet transform (自 R2022b 起)
dlfevalEvaluate deep learning model for custom training loops (自 R2019b 起)
dlgradientCompute gradients for custom training loops using automatic differentiation (自 R2019b 起)
dlhdl.TargetConfigure interface to target board for workflow deployment (自 R2020b 起)
dlhdl.WorkflowConfigure deployment workflow for deep learning neural network (自 R2020b 起)
dlmodwtDeep learning maximal overlap discrete wavelet transform and multiresolution analysis (自 R2022a 起)
dlmtimes(Not recommended) Batch matrix multiplication for deep learning (自 R2020a 起)
dlnetworkDeep learning network for custom training loops (自 R2019b 起)
dlode45Deep learning solution of nonstiff ordinary differential equation (ODE) (自 R2021b 起)
dlquantizationOptionsOptions for quantizing a trained deep neural network (自 R2020a 起)
dlquantizerQuantize a deep neural network to 8-bit scaled integer data types (自 R2020a 起)
dlstftDeep learning short-time Fourier transform (自 R2021a 起)
dltranspconvDeep learning transposed convolution (自 R2019b 起)
dlupdate Update parameters using custom function (自 R2019b 起)
doc2sequenceConvert documents to sequences for deep learning
dotprodDot product weight function
dropoutLayer丢弃层
edfheaderCreate header structure for EDF or EDF+ file (自 R2021a 起)
edfinfoGet information about EDF/EDF+ file (自 R2020b 起)
edfreadRead data from EDF/EDF+ file (自 R2020b 起)
edfwriteCreate or modify EDF or EDF+ file (自 R2021a 起)
efficientnetb0EfficientNet-b0 卷积神经网络 (自 R2020b 起)
elliot2sigElliot 2 symmetric sigmoid transfer function
elliotsigElliot symmetric sigmoid transfer function
elmannetElman neural network
eluLayerExponential linear unit (ELU) layer (自 R2019a 起)
embedEmbed discrete data (自 R2020b 起)
embeddingConcatenationLayerEmbedding concatenation layer (自 R2023b 起)
encodeEncode input data
EnergyDistributionDiscriminatorEnergy distribution discriminator (自 R2023a 起)
equalizeLayersEqualize layer parameters of deep neural network (自 R2022b 起)
errsurfError surface of single-input neuron
estimateNetworkMetricsEstimate network metrics for specific layers of a neural network (自 R2022a 起)
estimateNetworkOutputBounds Estimate output bounds of deep learning network (自 R2022b 起)
experiments.MonitorUpdate results table and training plots for custom training experiments (自 R2021a 起)
exportNetworkToTensorFlowExport Deep Learning Toolbox network or layer graph to TensorFlow (自 R2022b 起)
exportONNXNetworkExport network to ONNX model format
extendtsExtend time series data to given number of timesteps
extractdatadlarray 中提取数据 (自 R2019b 起)
fasterRCNNObjectDetectorDetect objects using Faster R-CNN deep learning detector
fastFlowAnomalyDetectorDetect anomalies using FastFlow network (自 R2023a 起)
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 (自 R2022b 起)
featureInputLayerFeature input layer (自 R2020b 起)
feedforwardnet生成前馈神经网络
filenames2labelsGet list of labels from filenames (自 R2022b 起)
findchangeptsFind abrupt changes in signal
finddimFind dimensions with specified label (自 R2019b 起)
findpeaks查找局部最大值
findPlaceholderLayersFind placeholder layers in network architecture imported from Keras or ONNX
fitnet函数拟合神经网络
fixunknownsProcess data by marking rows with unknown values
flattenLayerFlatten layer (自 R2019a 起)
folders2labelsGet list of labels from folder names (自 R2021a 起)
formwbForm bias and weights into single vector
forwardCompute deep learning network output for training (自 R2019b 起)
fpderivForward propagation derivative function
freezeParametersConvert learnable network parameters in ONNXParameters to nonlearnable (自 R2020b 起)
fromnndataConvert data from standard neural network cell array form
fScoreMetricDeep learning F-score metric (自 R2023b 起)
fullyconnectSum all weighted input data and apply a bias (自 R2019b 起)
fullyConnectedLayerFully connected layer
functionLayerFunction layer (自 R2021b 起)
functionToLayerGraph(To be removed) Convert deep learning model function to a layer graph (自 R2019b 起)
gadd广义加法
gdivide广义除法
geluApply Gaussian error linear unit (GELU) activation (自 R2022b 起)
geluLayerGaussian error linear unit (GELU) layer (自 R2022b 起)
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 (自 R2021b 起)
globalAveragePooling2dLayer2-D global average pooling layer (自 R2019b 起)
globalAveragePooling3dLayer3-D global average pooling layer (自 R2019b 起)
globalMaxPooling1dLayer1-D global max pooling layer (自 R2021b 起)
globalMaxPooling2dLayerGlobal max pooling layer (自 R2020a 起)
globalMaxPooling3dLayer3-D global max pooling layer (自 R2020a 起)
gmultiply广义乘法
gnegateGeneralized negation
googlenetGoogLeNet 卷积神经网络
gpu2nndataReformat neural data back from GPU
gradCAMExplain network predictions using Grad-CAM (自 R2021a 起)
gridtopGrid layer topology function
groupedConvolution2dLayer2-D grouped convolutional layer (自 R2019a 起)
groupnormNormalize data across grouped subsets of channels for each observation independently (自 R2020b 起)
groupNormalizationLayerGroup normalization layer (自 R2020b 起)
groupSubPlotGroup metrics in experiment training plot (自 R2021a 起)
groupSubPlotGroup metrics in training plot (自 R2022b 起)
gruGated recurrent unit (自 R2020a 起)
gruLayerGated recurrent unit (GRU) layer for recurrent neural network (RNN) (自 R2020a 起)
gruProjectedLayerGated recurrent unit (GRU) projected layer for recurrent neural network (RNN) (自 R2023b 起)
gsqrtGeneralized square root
gsubtract广义减法
hardlim硬限制传递函数
hardlims对称硬限制传递函数
hasdataDetermine if minibatchqueue can return mini-batch (自 R2020b 起)
HBOSDistributionDiscriminatorHBOS distribution discriminator (自 R2023a 起)
hextopHexagonal layer topology function
huberHuber loss for regression tasks (自 R2021a 起)
image3dInputLayer3-D image input layer (自 R2019a 起)
imageDataAugmenterConfigure image data augmentation
imageDatastore图像数据的数据存储
imageInputLayerImage input layer
imageLIMEExplain network predictions using LIME (自 R2020b 起)
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
importNetworkFromONNXImport ONNX network as MATLAB network (自 R2023b 起)
importNetworkFromPyTorchImport PyTorch network as MATLAB network (自 R2022b 起)
importNetworkFromTensorFlowImport TensorFlow network as MATLAB network (自 R2023b 起)
importONNXFunctionImport pretrained ONNX network as a function (自 R2020b 起)
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 (自 R2021a 起)
importTensorFlowNetwork(To be removed) Import pretrained TensorFlow network (自 R2021a 起)
inceptionresnetv2预训练 Inception-ResNet-v2 卷积神经网络
inceptionv3Inception-v3 卷积神经网络
ind2vecConvert indices to vectors
ind2wordMap encoding index to word
indexing1dLayer1-D indexing layer (自 R2023b 起)
initInitialize neural network
initconConscience bias initialization function
initializeInitialize learnable and state parameters of a dlnetwork (自 R2021a 起)
initlay逐层网络初始化函数
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 (自 R2021a 起)
instanceNormalizationLayerInstance normalization layer (自 R2021a 起)
isconfiguredIndicate if network inputs and outputs are configured
isdlarrayCheck if object is dlarray (自 R2020b 起)
isequalCheck equality of deep learning layer graphs or networks (自 R2021a 起)
isequalnCheck equality of deep learning layer graphs or networks ignoring NaN values (自 R2021a 起)
isInNetworkDistributionDetermine whether data is within the distribution of the network (自 R2023a 起)
isVocabularyWordTest if word is member of word embedding or encoding
l1lossL1 loss for regression tasks (自 R2021b 起)
l2lossL2 loss for regression tasks (自 R2021b 起)
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 (自 R2021a 起)
layerNormalizationLayerLayer normalization layer (自 R2021a 起)
layrecnetLayer recurrent neural network
lbfgsStateState of limited-memory BFGS (L-BFGS) solver (自 R2023a 起)
lbfgsupdateUpdate parameters using limited-memory BFGS (L-BFGS) (自 R2023a 起)
leakyreluApply leaky rectified linear unit activation (自 R2019b 起)
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 (自 R2022a 起)
logsigLog-sigmoid 传递函数
lstmLong short-term memory (自 R2019b 起)
lstmLayerLong short-term memory (LSTM) layer for recurrent neural network (RNN)
lstmProjectedLayerLong short-term memory (LSTM) projected layer for recurrent neural network (RNN) (自 R2022b 起)
lvqnetLearning vector quantization neural network
lvqoutputsLVQ outputs processing function
mae均值绝对误差性能函数
mandistManhattan distance weight function
mapminmax通过将行最小值和最大值映射到 [-1 1] 来处理矩阵
mapstdProcess matrices by mapping each row’s means to 0 and deviations to 1
maskrcnnDetect objects using Mask R-CNN instance segmentation (自 R2021b 起)
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 (自 R2019b 起)
maxPooling1dLayer1-D max pooling layer (自 R2021b 起)
maxPooling2dLayerMax pooling layer
maxPooling3dLayer3-D max pooling layer (自 R2019a 起)
maxunpoolUnpool the output of a maximum pooling operation (自 R2019b 起)
maxUnpooling2dLayerMax unpooling layer
meanabs一个或多个矩阵包含的绝对值元素的均值
meansqrMean of squared elements of matrix or matrices
midpointMidpoint weight initialization function
minibatchqueueCreate mini-batches for deep learning (自 R2020b 起)
minmax矩阵行的范围
mobilenetv2MobileNet-v2 卷积神经网络 (自 R2019a 起)
modwtMaximal overlap discrete wavelet transform
modwtLayerMaximal overlap discrete wavelet transform (MODWT) layer (自 R2022b 起)
mseHalf mean squared error (自 R2019b 起)
mse均方归一化误差性能函数
multiplicationLayerMultiplication layer (自 R2020b 起)
narnetNonlinear autoregressive neural network
narxnetNonlinear autoregressive neural network with external input
nasnetlarge预训练 NASNet-Large 卷积神经网络 (自 R2019a 起)
nasnetmobile预训练的 NASNet-Mobile 卷积神经网络 (自 R2019a 起)
nctool打开神经网络聚类
negdistNegative distance weight function
netinv逆传递函数
netprodProduct net input function
netsumSum net input function
networkConvert Autoencoder object into network object
network创建自定义浅层神经网络
networkDataLayoutDeep learning network data layout for learnable parameter initialization (自 R2022b 起)
networkDistributionDiscriminator Deep learning distribution discriminator (自 R2023a 起)
neuralODELayerNeural ODE layer (自 R2023b 起)
neuronPCAPrincipal component analysis of neuron activations (自 R2022b 起)
newgrnn设计广义回归神经网络
newlindDesign linear layer
newpnnDesign probabilistic neural network
newrb设计径向基网络
newrbe设计精确的径向基网络
nextObtain next mini-batch of data from minibatchqueue (自 R2020b 起)
nftool打开神经网络拟合
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(已删除)打开网络/数据管理器
nntraintool(Removed) Neural network training tool
noloopRemove neural network open- and closed-loop feedback
normc归一化矩阵的列
normprodNormalized dot product weight function
normr归一化矩阵的行
nprtool打开神经网络模式识别
ntstool打开神经网络时间序列
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 (自 R2019b 起)
ODINDistributionDiscriminatorODIN distribution discriminator (自 R2023a 起)
onehotdecodeDecode probability vectors into class labels (自 R2020b 起)
onehotencodeEncode data labels into one-hot vectors (自 R2020b 起)
ONNXParametersParameters of imported ONNX network for deep learning (自 R2020b 起)
openl3OpenL3 neural network (自 R2021a 起)
openl3EmbeddingsExtract OpenL3 feature embeddings (自 R2022a 起)
openloopConvert neural network closed-loop feedback to open loop
paddataPad data by adding elements (自 R2023b 起)
padsequencesPad or truncate sequence data to same length (自 R2021a 起)
partitionPartition minibatchqueue (自 R2020b 起)
partitionByIndexPartition augmentedImageDatastore according to indices
patchCoreAnomalyDetectorDetect anomalies using PatchCore network (自 R2023a 起)
patchEmbeddingLayerPatch embedding layer (自 R2023b 起)
patternnet生成模式识别网络
perceptron简单的单层二类分类器
performCalculate network performance
pitchnnEstimate pitch with deep learning neural network (自 R2021a 起)
pixelLabelDatastoreDatastore for pixel label data
PlaceholderLayerLayer replacing an unsupported Keras or ONNX layer
plot绘制神经网络架构
plotPlot receiver operating characteristic (ROC) curves and other performance curves (自 R2022b 起)
plotconfusion绘制分类混淆矩阵
plotepPlot weight-bias position on error surface
ploterrcorrPlot autocorrelation of error time series
ploterrhist绘图误差直方图
plotesPlot error surface of single-input neuron
plotfit绘图函数拟合
plotinerrcorrPlot input to error time-series cross-correlation
plotpcPlot classification line on perceptron vector plot
plotperform绘制网络性能图
plotpv绘制感知器输入/目标向量
plotregression绘制线性回归图
plotresponsePlot dynamic network time series response
plotroc绘制受试者工作特征图
plotsomPlot self-organizing map
plotsomhits绘制自组织映射采样命中数
plotsomncPlot self-organizing map neighbor connections
plotsomndPlot self-organizing map neighbor distances
plotsomplanesPlot self-organizing map weight planes
plotsomposPlot self-organizing map weight positions
plotsomtop绘制自组织映射拓扑
plottrainstate绘制训练状态值图
plotv(To be removed) Plot vectors as lines from origin
plotvecPlot vectors with different colors
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 (自 R2021b 起)
pointPillarsObjectDetectorPointPillars object detector (自 R2021b 起)
positionEmbeddingLayerPosition embedding layer (自 R2023b 起)
poslin正线性传递函数
precisionMetricDeep learning precision metric (自 R2023b 起)
predictPredict responses using trained deep learning neural network
predictCompute deep learning network output for inference (自 R2019b 起)
predictCompute deep learning network output for inference by using a TensorFlow Lite model (自 R2022a 起)
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
ProjectedLayerCompressed neural network layer via projection (自 R2023b 起)
pruneDelete neural inputs, layers, and outputs with sizes of zero
prunedataPrune data for consistency with pruned network
purelin线性传递函数
quant将值离散化为数量的倍数
quantizationDetailsDisplay quantization details for a neural network (自 R2022a 起)
quantizeQuantize deep neural network (自 R2022a 起)
radbas径向基传递函数
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
rands对称随机权重/偏置初始化函数
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
recallMetricDeep learning recall metric (自 R2023b 起)
recordMetricsRecord metric values in experiment results table and training plot (自 R2021a 起)
recordMetricsRecord metric values for custom training loops (自 R2022b 起)
regression(Not recommended) Perform linear regression of shallow network outputs on targets
regressionLayer回归输出层
RegressionOutputLayer回归输出层
relu应用修正线性单元激活 (自 R2019b 起)
reluLayer修正线性单元 (ReLU) 层
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 (自 R2020b 起)
removerowsProcess matrices by removing rows with specified indices
replaceLayerReplace layer in layer graph or network
resetReset minibatchqueue to start of data (自 R2020b 起)
resetStateReset state parameters of neural network
resizeResize data by adding or removing elements (自 R2023b 起)
resnet101ResNet-101 卷积神经网络
resnet18ResNet-18 卷积神经网络
resnet3dLayersCreate 3-D residual network (自 R2021b 起)
resnet50ResNet-50 卷积神经网络
resnetLayersCreate 2-D residual network (自 R2021b 起)
revertChange network weights and biases to previous initialization values
risetime Rise time of positive-going bilevel waveform transitions
rmseMetricDeep learning root mean squared error metric (自 R2023b 起)
rmspropupdate Update parameters using root mean squared propagation (RMSProp) (自 R2019b 起)
rocReceiver operating characteristic
rocmetricsReceiver operating characteristic (ROC) curve and performance metrics for binary and multiclass classifiers (自 R2022b 起)
saeSum absolute error performance function
satlin饱和线性传递函数
satlins对称饱和线性传递函数
scalprodScalar product weight function
segmentCells2DSegment 2-D image using Cellpose (自 R2023b 起)
segmentCells3DSegment 3-D image volume using Cellpose (自 R2023b 起)
segnetLayersCreate SegNet layers for semantic segmentation
selfAttentionLayerSelf-attention layer (自 R2023a 起)
selforgmap自组织映射
separateSpeakersSeparate signal by speakers (自 R2023b 起)
separatewbSeparate biases and weight values from weight/bias vector
seq2conConvert sequential vectors to concurrent vectors
sequenceFoldingLayerSequence folding layer (自 R2019a 起)
sequenceInputLayerSequence input layer
sequenceUnfoldingLayerSequence unfolding layer (自 R2019a 起)
SeriesNetwork用于深度学习的串行网络
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) (自 R2019b 起)
showShow training information plot (自 R2023b 起)
shuffleShuffle data in augmentedImageDatastore
shuffleShuffle data in minibatchqueue (自 R2020b 起)
shufflenet预训练 ShuffleNet 卷积神经网络 (自 R2019a 起)
sigmoid应用 sigmoid 激活 (自 R2019b 起)
sigmoidLayerSigmoid layer (自 R2020b 起)
signalDatastoreDatastore for collection of signals (自 R2020a 起)
signalFrequencyFeatureExtractorStreamline signal frequency feature extraction (自 R2021b 起)
signalLabelDefinitionCreate signal label definition
signalMaskModify and convert signal masks and extract signal regions of interest (自 R2020b 起)
signalTimeFeatureExtractorStreamline signal time feature extraction (自 R2021a 起)
sigrangebinmaskLabel signal samples with values within a specified range (自 R2023a 起)
simSimulate neural network
sim2nndataConvert Simulink time series to neural network data
sinusoidalPositionEncodingLayerSinusoidal position encoding layer (自 R2023b 起)
softmaxApply softmax activation to channel dimension (自 R2019b 起)
softmaxsoftmax 传递函数
softmaxLayerSoftmax 层
solov2Segment objects using SOLOv2 instance segmentation network (自 R2023b 起)
sortClassesSort classes of confusion matrix chart
splitlabelsFind indices to split labels according to specified proportions (自 R2021a 起)
squeezenetSqueezeNet 卷积神经网络
squeezesegv2LayersCreate SqueezeSegV2 segmentation network for organized lidar point cloud (自 R2020b 起)
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 (自 R2020a 起)
sseSum squared error performance function
stackStack encoders from several autoencoders together
staticderivStatic derivative function
stftShort-time Fourier transform (自 R2019a 起)
stftLayerShort-time Fourier transform layer (自 R2021b 起)
stftmag2sigSignal reconstruction from STFT magnitude (自 R2020b 起)
stripdimsRemove dlarray data format (自 R2019b 起)
sumabs一个或多个矩阵的绝对元素之和
summaryPrint network summary (自 R2022b 起)
sumsqr一个或多个矩阵的元素的平方和
swishLayerSwish layer (自 R2021a 起)
tanhLayer双曲正切 (tanh) 层 (自 R2019a 起)
tansig双曲正切 sigmoid 传递函数
tapdelayShift neural network time series data for tap delay
taylorPrunableNetworkNetwork that can be pruned by using first-order Taylor approximation (自 R2022a 起)
TFLiteModelTensorFlow Lite model (自 R2022a 起)
timedelaynetTime delay neural network
tonndataConvert data to standard neural network cell array form
train训练浅层神经网络
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
TrainingInfoNeural network training information (自 R2023b 起)
trainingOptionsOptions for training deep learning neural network
TrainingOptionsADAMTraining options for Adam optimizer
TrainingOptionsLBFGSTraining options for limited-memory BFGS (L-BFGS) optimizer (自 R2023b 起)
TrainingOptionsRMSPropTraining options for RMSProp optimizer
TrainingOptionsSGDMTraining options for stochastic gradient descent with momentum
trainingProgressMonitorMonitor and plot training progress for deep learning custom training loops (自 R2022b 起)
trainlm莱文贝格-马夸特反向传播
trainnetTrain deep learning neural network (自 R2023b 起)
trainNetwork训练神经网络
trainossOne-step secant backpropagation
trainPointPillarsObjectDetectorTrain PointPillars object detector (自 R2021b 起)
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
transform变换数据存储 (自 R2019a 起)
TransformedDatastore用于变换基础数据存储的数据存储 (自 R2019a 起)
transposedConv1dLayerTransposed 1-D convolution layer (自 R2022a 起)
transposedConv2dLayerTransposed 2-D convolution layer
transposedConv3dLayerTransposed 3-D convolution layer (自 R2019a 起)
TransposedConvolution1DLayerTransposed 1-D convolution layer (自 R2022a 起)
TransposedConvolution2DLayerTransposed 2-D convolution layer
TransposedConvolution3dLayerTransposed 3-D convolution layer (自 R2019a 起)
tribas三角形基传递函数
trimdataTrim data by removing elements (自 R2023b 起)
tritopTriangle layer topology function
unconfigureUnconfigure network inputs and outputs
unet3dLayersCreate 3-D U-Net layers for semantic segmentation of volumetric images (自 R2019b 起)
unetLayersCreate U-Net layers for semantic segmentation
unfreezeParametersConvert nonlearnable network parameters in ONNXParameters to learnable (自 R2020b 起)
unpackProjectedLayersUnpack projected layers of neural network (自 R2023b 起)
updateInfoUpdate information columns in experiment results table (自 R2021a 起)
updateInfoUpdate information values for custom training loops (自 R2022b 起)
updatePrunablesRemove filters from prunable layers based on importance scores (自 R2022a 起)
updateScoreCompute and accumulate Taylor-based importance scores for pruning (自 R2022a 起)
vadnetVoice activity detection (VAD) neural network (自 R2023a 起)
validateQuantize and validate a deep neural network (自 R2020a 起)
vec2indConvert vectors to indices
vec2wordMap embedding vector to word
verifyNetworkRobustnessVerify adversarial robustness of deep learning network (自 R2022b 起)
vgg16VGG-16 卷积神经网络
vgg19VGG-19 卷积神经网络
vggishVGGish neural network (自 R2020b 起)
vggishEmbeddingsExtract VGGish feature embeddings (自 R2022a 起)
view查看浅层神经网络
viewView autoencoder
visionTransformerPretrained vision transformer (ViT) neural network (自 R2023b 起)
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 卷积神经网络 (自 R2019a 起)
yamnetYAMNet neural network (自 R2020b 起)
yolov2ObjectDetectorDetect objects using YOLO v2 object detector (自 R2019a 起)
yolov3ObjectDetectorDetect objects using YOLO v3 object detector (自 R2021a 起)
yolov4ObjectDetectorDetect objects using YOLO v4 object detector (自 R2022a 起)
yoloxObjectDetectorDetect objects using YOLOX object detector (自 R2023b 起)