Deep Learning Toolbox
Version 23.2 (R2023b) 01-Aug-2023
Training for Deep Learning
assembleNetwork - Assemble a neural network from pretrained layers
augmentedImageDatastore - Generate batches of augmented image data
imageDataAugmenter - Configure image data augmentation
dlnetwork - Neural network for custom training
trainNetwork - Train a neural network
trainingOptions - Options for training a neural network
Layers for Deep Learning
additionLayer - Addition layer
averagePooling2dLayer - 2-D average pooling layer
averagePooling3dLayer - 3-D average pooling layer
batchNormalizationLayer - Batch normalization layer
bilstmLayer - Bidirectional long short-term memory (biLSTM) layer
classificationLayer - Classification output layer for a neural network
clippedReluLayer - Clipped rectified linear unit (ReLU) layer
concatenationLayer - Concatenation layer
convolution2dLayer - 2-D convolution layer for Convolutional Neural Networks
convolution3dLayer - 3-D convolution layer for Convolutional Neural Networks
crop2dLayer - 2-D crop layer
crop3dLayer - 3-D crop layer
crossChannelNormalizationLayer - Local response normalization along channels
depthConcatenationLayer - Depth concatenation layer
dropoutLayer - Dropout layer
eluLayer - Exponential linear unit (ELU) layer
featureInputLayer - Feature input layer
flattenLayer - Flatten layer
fullyConnectedLayer - Fully connected layer
globalAveragePooling2dLayer - 2-D global average pooling layer
globalAveragePooling3dLayer - 3-D global average pooling layer
globalMaxPooling2dLayer - 2-D global max pooling layer
globalMaxPooling3dLayer - 3-D global max pooling layer
groupedConvolution2dLayer - 2-D grouped convolution layer
groupNormalizationLayer - Group normalization layer
gruLayer - Gated recurrent unit (GRU) layer
imageInputLayer - Image input layer
image3dInputLayer - 3-D image input layer
instanceNormalizationLayer - Instance normalization layer
layerNormalizationLayer - Layer normalization layer
leakyReluLayer - Leaky rectified linear unit (ReLU) layer
lstmLayer - Long short-term memory (LSTM) layer
maxPooling2dLayer - 2-D max pooling layer
maxPooling3dLayer - 3-D max pooling layer
maxUnpooling2dLayer - Max unpooling layer
multiplicationLayer - Element-wise Multiplication layer
regressionLayer - Regression output layer for a neural network
reluLayer - Rectified linear unit (ReLU) layer
sequenceFoldingLayer - Sequence folding layer
sequenceInputLayer - Sequence input layer
sequenceUnfoldingLayer - Sequence unfolding layer
sigmoidLayer - Sigmoid layer
softmaxLayer - Softmax layer
swishLayer - Swish layer
tanhLayer - Hyperbolic tangent layer
transposedConv2dLayer - 2-D transposed convolution layer
transposedConv3dLayer - 3-D transposed convolution layer
Custom Layers for Deep Learning
checkLayer - Check layer validity
findPlaceholderLayers - Find placeholder layers in a layer graph or layer array
Apps for Deep Learning
analyzeNetwork - Analyze deep learning networks
deepNetworkDesigner - Design and edit deep learning networks
experimentManager - Design and run experiments to train and compare deep learning networks
deepNetworkQuantizer - Quantize deep learning networks for deployment
Extract and Visualize Features, Predict Outcomes for Deep Learning
deepDreamImage - Visualize network features using Deep Dream
occlusionSensitivity - Explain network predictions by occluding the inputs
imageLIME - Explain network predictions using LIME
gradCAM - Explain network predictions using Grad-CAM
layerGraph - Create a layer graph
confusionmat - Confusion matrix for classification algorithms
confusionchart - Plot a confusion matrix
Using Pretrained Networks for Deep Learning
alexnet - Pretrained AlexNet convolutional neural network
darknet19 - Pretrained DarkNet-19 convolutional neural network
darknet53 - Pretrained DarkNet-53 convolutional neural network
densenet201 - Pretrained DenseNet-201 convolutional neural network
googlenet - Pretrained GoogLeNet convolutional neural network
inceptionv3 - Pretrained Inception-v3 convolutional neural network
inceptionresnetv2 - Pretrained Inception-ResNet-v2 convolutional neural network
mobilenetv2 - Pretrained MobileNetV2 convolutional neural network
nasnetmobile - Pretrained NASNet-Mobile convolutional neural network
nasnetlarge - Pretrained NASNet-Large convolutional neural network
resnet18 - Pretrained ResNet-18 convolutional neural network
resnet50 - Pretrained ResNet-50 convolutional neural network
resnet101 - Pretrained ResNet-101 convolutional neural network
squeezenet - Pretrained SqueezeNet convolutional neural network
shufflenet - Pretrained ShuffleNet convolutional neural network
vgg16 - Pretrained VGG-16 convolutional neural network
vgg19 - Pretrained VGG-19 convolutional neural network
xception - Pretrained Xception convolutional neural network
importCaffeLayers - Import Convolutional Neural Network Layers from Caffe
importCaffeNetwork - Import Convolutional Neural Network Models from Caffe
importKerasLayers - Import Convolutional Neural Network Layers from Keras
importKerasNetwork - Import Convolutional Neural Network Models from Keras
importONNXFunction - Import Convolutional Neural Network Function from ONNX Format
importONNXLayers - Import Convolutional Neural Network Layers from ONNX Format
importONNXNetwork - Import Convolutional Neural Network Models from ONNX Format
exportONNXNetwork - Export Convolutional Neural Network Models to ONNX Format
importTensorFlowLayers - Import Convolutional Neural Network Layers from TensorFlow
importTensorFlowNetwork - Import Convolutional Neural Network Models from TensorFlow
exportNetworkToTensorFlow - Export Convolutional Neural Network Models to TensorFlow
Graphical User Interface Functions for Shallow Neural Networks
nnstart - Neural Network Start GUI
nctool - Neural Classification app
nftool - Neural Fitting app
nntraintool - Neural Network Training Tool
nprtool - Neural Pattern Recognition app
ntstool - Neural Time Series app
view - View a neural network.
Shallow Neural Network Creation Functions
cascadeforwardnet - Cascade-forward neural network.
competlayer - Competitive neural layer.
distdelaynet - Distributed delay neural network.
elmannet - Elman neural network.
feedforwardnet - Feed-forward neural network.
fitnet - Function fitting neural network.
layrecnet - Layered recurrent neural network.
linearlayer - Linear neural layer.
lvqnet - Learning vector quantization (LVQ) neural network.
narnet - Nonlinear auto-associative time-series network.
narxnet - Nonlinear auto-associative time-series network with external input.
newgrnn - Design a generalized regression neural network.
newhop - Create a Hopfield recurrent network.
newlind - Design a linear layer.
newpnn - Design a probabilistic neural network.
newrb - Design a radial basis network.
newrbe - Design an exact radial basis network.
patternnet - Pattern recognition neural network.
perceptron - Perceptron.
selforgmap - Self-organizing map.
timedelaynet - Time-delay neural network.
Using Shallow Neural Networks
network - Create a custom neural network.
sim - Simulate a neural network.
init - Initialize a neural network.
adapt - Allow a neural network to adapt.
train - Train a neural network.
disp - Display a neural network’s properties.
display - Display the name and properties of a neural network
adddelay - Add a delay to a neural network’s response.
closeloop - Convert neural network open feedback to closed feedback loops.
formwb - Form bias and weights into single vector.
getwb - Get all network weight and bias values as a single vector.
noloop - Remove neural network open and closed feedback loops.
openloop - Convert neural network closed feedback to open feedback loops.
removedelay - Remove a delay to a neural network’s response.
separatewb - Separate biases and weights from a weight/bias vector.
setwb - Set all network weight and bias values with a single vector.
Simulink Support for Shallow Neural Networks
gensim - Generate a Simulink block to simulate a neural network.
setsiminit - Set neural network Simulink block initial conditions
getsiminit - Get neural network Simulink block initial conditions
neural - Neural network Simulink blockset.
Training Functions for Shallow Neural Networks
trainb - Batch training with weight & bias learning rules.
trainbfg - BFGS quasi-Newton backpropagation.
trainbr - Bayesian Regulation backpropagation.
trainbu - Unsupervised batch training with weight & bias learning rules.
trainc - Cyclical order weight/bias training.
traincgb - Conjugate gradient backpropagation with Powell-Beale restarts.
traincgf - Conjugate gradient backpropagation with Fletcher-Reeves updates.
traincgp - Conjugate gradient backpropagation with Polak-Ribiere updates.
traingd - Gradient descent backpropagation.
traingda - Gradient descent with adaptive lr backpropagation.
traingdm - Gradient descent with momentum.
traingdx - Gradient descent w/momentum & adaptive lr backpropagation.
trainlm - Levenberg-Marquardt backpropagation.
trainoss - One step secant backpropagation.
trainr - Random order weight/bias training.
trainrp - RPROP backpropagation.
trainru - Unsupervised random order weight/bias training.
trains - Sequential order weight/bias training.
trainscg - Scaled conjugate gradient backpropagation.
Plotting Functions for Shallow Neural Networks
plotconfusion - Plot classification confusion matrix.
ploterrcorr - Plot autocorrelation of error time series.
ploterrhist - Plot error histogram.
plotfit - Plot function fit.
plotinerrcorr - Plot input to error time series cross-correlation.
plotperform - Plot network performance.
plotregression - Plot linear regression.
plotresponse - Plot dynamic network time-series response.
plotroc - Plot receiver operating characteristic.
plotsomhits - Plot self-organizing map sample hits.
plotsomnc - Plot Self-organizing map neighbor connections.
plotsomnd - Plot Self-organizing map neighbor distances.
plotsomplanes - Plot self-organizing map weight planes.
plotsompos - Plot self-organizing map weight positions.
plotsomtop - Plot self-organizing map topology.
plottrainstate - Plot training state values.
plotwb - Plot Hinton diagrams of weight and bias values.
List of other Shallow Neural Network Implementation Functions
nnadapt - Adapt functions.
nnderivative - Derivative functions.
nndistance - Distance functions.
nndivision - Division functions.
nninitlayer - Initialize layer functions.
nninitnetwork - Initialize network functions.
nninitweight - Initialize weight functions.
nnlearn - Learning functions.
nnnetinput - Net input functions.
nnperformance - Performance functions.
nnprocess - Processing functions.
nnsearch - Line search functions.
nntopology - Topology functions.
nntransfer - Transfer functions.
nnweight - Weight functions.
Obsolete Functions
nntool - replaced by nnstart