Documentation

This is machine translation

Translated by Microsoft
Mouseover text to see original. Click the button below to return to the English verison of the page.

Note: This page has been translated by MathWorks. Please click here
To view all translated materals including this page, select Japan from the country navigator on the bottom of this page.

Neural Network Toolbox Functions

Alphabetical List By Category

Deep Learning Basics

alexnetPretrained AlexNet convolutional neural network
vgg16Pretrained VGG-16 convolutional neural network
vgg19Pretrained VGG-19 convolutional neural network
googlenetPretrained GoogLeNet convolutional neural network
importCaffeNetworkImport pretrained convolutional neural network models from Caffe
trainingOptionsOptions for training neural network
trainNetworkTrain neural network for deep learning

Deep Learning Image Classification

alexnetPretrained AlexNet convolutional neural network
vgg16Pretrained VGG-16 convolutional neural network
vgg19Pretrained VGG-19 convolutional neural network
googlenetPretrained GoogLeNet convolutional neural network
importCaffeNetworkImport pretrained convolutional neural network models from Caffe
trainingOptionsOptions for training neural network
trainNetworkTrain neural network for deep learning
imageDataAugmenterConfigure image data augmentation
augmentedImageSourceGenerate batches of augmented image data

Deep Learning Training from Scratch

alexnetPretrained AlexNet convolutional neural network
vgg16Pretrained VGG-16 convolutional neural network
vgg19Pretrained VGG-19 convolutional neural network
googlenetPretrained GoogLeNet convolutional neural network
importCaffeLayersImport convolutional neural network layers from Caffe
importCaffeNetworkImport pretrained convolutional neural network models from Caffe
imageInputLayerImage input layer
sequenceInputLayerSequence input layer
convolution2dLayer2-D convolutional layer
transposedConv2dLayerTransposed 2-D convolution layer
fullyConnectedLayerFully connected layer
LSTMLayerLong short-term memory (LSTM) layer
reluLayerRectified Linear Unit (ReLU) layer
leakyReluLayerLeaky Rectified Linear Unit (ReLU) layer
clippedReluLayerClipped Rectified Linear Unit (ReLU) layer
batchNormalizationLayerBatch normalization layer
crossChannelNormalizationLayer Channel-wise local response normalization layer
dropoutLayerDropout layer
averagePooling2dLayerAverage pooling layer
maxPooling2dLayerMax pooling layer
maxUnpooling2dLayerMax unpooling layer
additionLayerAddition layer
depthConcatenationLayerDepth concatenation layer
softmaxLayerSoftmax layer
classificationLayerCreate classification output layer
regressionLayerCreate a regression output layer
setLearnRateFactorSet learn rate factor of layer learnable parameter
setL2FactorSet L2 regularization factor of layer learnable parameter
getLearnRateFactorGet learn rate factor of layer learnable parameter
getL2FactorGet L2 regularization factor of layer learnable parameter
trainingOptionsOptions for training neural network
trainNetworkTrain neural network for deep learning
SeriesNetworkSeries network for deep learning
DAGNetworkDirected acyclic graph (DAG) network for deep learning
imageDataAugmenterConfigure image data augmentation
augmentedImageSourceGenerate batches of augmented image data
layerGraphGraph of network layers for deep learning
plotPlot neural network layer graph
addLayersAdd layers to layer graph
connectLayersConnect layers in layer graph
removeLayersRemove layers from layer graph
disconnectLayersDisconnect layers in layer graph
DAGNetworkDirected acyclic graph (DAG) network for deep learning
predictPredict responses using a trained deep learning neural network
classifyClassify data using a trained deep learning neural network
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 the state of a recurrent neural network

Deep Learning Tuning and Visualization

trainingOptionsOptions for training neural network
trainNetworkTrain neural network for deep learning
activationsCompute convolutional neural network layer activations
predictPredict responses using a trained deep learning neural network
classifyClassify data using a trained deep learning neural network
deepDreamImageVisualize network features using deep dream

Function Approximation and Clustering

Function Approximation and Nonlinear Regression

nnstartNeural network getting started GUI
viewView neural network
fitnetFunction fitting neural network
feedforwardnetFeedforward neural network
cascadeforwardnetCascade-forward neural network
trainTrain neural network
trainlmLevenberg-Marquardt backpropagation
trainbrBayesian regularization backpropagation
trainscgScaled conjugate gradient backpropagation
trainrpResilient backpropagation
mseMean squared normalized error performance function
regressionLinear regression
ploterrhistPlot error histogram
plotfitPlot function fit
plotperformPlot network performance
plotregressionPlot linear regression
plottrainstatePlot training state values
genFunctionGenerate MATLAB function for simulating neural network

Pattern Recognition

AutoencoderAutoencoder class
nnstartNeural network getting started GUI
viewView neural network
trainAutoencoderTrain an autoencoder
trainSoftmaxLayerTrain a softmax layer for classification
decodeDecode encoded data
encodeEncode input data
predictReconstruct the inputs using trained autoencoder
stackStack encoders from several autoencoders together
networkConvert Autoencoder object into network object
patternnetPattern recognition network
lvqnetLearning vector quantization neural network
trainTrain neural network
trainlmLevenberg-Marquardt backpropagation
trainbrBayesian regularization backpropagation
trainscgScaled conjugate gradient backpropagation
trainrpResilient backpropagation
mseMean squared normalized error performance function
regressionLinear regression
rocReceiver operating characteristic
plotconfusionPlot classification confusion matrix
ploterrhistPlot error histogram
plotperformPlot network performance
plotregressionPlot linear regression
plotrocPlot receiver operating characteristic
plottrainstatePlot training state values
crossentropyNeural network performance
genFunctionGenerate MATLAB function for simulating neural network

Clustering

Self-Organizing Maps

nnstartNeural network getting started GUI
viewView neural network
selforgmapSelf-organizing map
trainTrain neural network
plotsomhitsPlot self-organizing map sample hits
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
genFunctionGenerate MATLAB function for simulating neural network

Competitive Layers

competlayerCompetitive layer
viewView neural network
trainTrain neural network
trainruUnsupervised random order weight/bias training
learnkKohonen weight learning function
learnconConscience bias learning function
genFunctionGenerate MATLAB function for simulating neural network

Autoencoders

AutoencoderAutoencoder class
trainAutoencoderTrain an autoencoder
trainSoftmaxLayerTrain a softmax layer for classification
decodeDecode encoded data
encodeEncode input data
generateFunctionGenerate a MATLAB function to run the autoencoder
generateSimulinkGenerate a Simulink model for the autoencoder
networkConvert Autoencoder object into network object
plotWeightsPlot a visualization of the weights for the encoder of an autoencoder
predictReconstruct the inputs using trained autoencoder
stackStack encoders from several autoencoders together
viewView autoencoder

Define Shallow Neural Network Architectures

networkCreate custom neural network

Time Series and Control Systems

Time Series and Dynamic Systems

Modeling and Prediction with NARX and Time-Delay Networks

nnstartNeural network getting started GUI
viewView neural network
timedelaynetTime delay neural network
narxnetNonlinear autoregressive neural network with external input
narnetNonlinear autoregressive neural network
layrecnetLayer recurrent neural network
distdelaynetDistributed delay network
trainTrain neural network
gensimGenerate Simulink block for neural network simulation
adddelayAdd delay to neural network response
removedelayRemove delay to neural network’s response
closeloopConvert neural network open-loop feedback to closed loop
openloopConvert neural network closed-loop feedback to open loop
ploterrhistPlot error histogram
plotinerrcorrPlot input to error time-series cross-correlation
plotregressionPlot linear regression
plotresponsePlot dynamic network time series response
ploterrcorrPlot autocorrelation of error time series
genFunctionGenerate MATLAB function for simulating neural network
gensimGenerate Simulink block for neural network simulation
setsiminitSet neural network Simulink block initial conditions
getsiminitGet Simulink neural network block initial input and layer delays states
sim2nndataConvert Simulink time series to neural network data
nndata2simConvert neural network data to Simulink time series
Was this topic helpful?