Main Content

Built-In Training

Train deep learning networks using built-in training functions

After defining the network architecture, you can define training parameters using the trainingOptions function. You can then train the network using the trainnet function. Use the trained network to predict class labels or numeric responses.

Apps

Deep Network DesignerDesign and visualize deep learning networks

Functions

expand all

dlnetworkDeep learning neural network
trainingOptionsOptions for training deep learning neural network
trainnetTrain deep learning neural network (Since R2023b)
TrainingInfoNeural network training information (Since R2023b)
showShow training information plot (Since R2023b)
closeClose training information plot (Since R2023b)
piecewiseLearnRatePiecewise learning rate schedule (Since R2024b)
warmupLearnRateWarm-up learning rate schedule (Since R2024b)
polynomialLearnRatePolynomial learning rate schedule (Since R2024b)
exponentialLearnRateExponential learning rate schedule (Since R2024b)
cosineLearnRateCosine learning rate schedule (Since R2024b)
cyclicalLearnRateCyclical learning rate schedule (Since R2024b)
testnetTest deep learning neural network (Since R2024b)
accuracyMetricDeep learning accuracy metric (Since R2023b)
aucMetricDeep learning area under ROC curve (AUC) metric (Since R2023b)
fScoreMetricDeep learning F-score metric (Since R2023b)
precisionMetricDeep learning precision metric (Since R2023b)
recallMetricDeep learning recall metric (Since R2023b)
rmseMetricDeep learning root mean squared error metric (Since R2023b)
predictCompute deep learning network output for inference
minibatchpredictMini-batched neural network prediction (Since R2024a)
scores2labelConvert prediction scores to labels (Since R2024a)
confusionchartCreate confusion matrix chart for classification problem
sortClassesSort classes of confusion matrix chart
classifyAndUpdateState(Not recommended) Classify data using a trained recurrent neural network and update the network state

Topics

Featured Examples