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.


Deep Network DesignerProgetta, visualizza e addestra le reti di Deep Learning


espandi tutto

dlnetworkDeep learning neural network (Da R2019b)
trainingOptionsOpzioni per l’addestramento della rete neurale di Deep Learning
trainnetTrain deep learning neural network (Da R2023b)
TrainingInfoNeural network training information (Da R2023b)
showShow training information plot (Da R2023b)
closeClose training information plot (Da R2023b)
accuracyMetricDeep learning accuracy metric (Da R2023b)
aucMetricDeep learning area under ROC curve (AUC) metric (Da R2023b)
fScoreMetricDeep learning F-score metric (Da R2023b)
precisionMetricDeep learning precision metric (Da R2023b)
recallMetricDeep learning recall metric (Da R2023b)
rmseMetricDeep learning root mean squared error metric (Da R2023b)
predictCompute deep learning network output for inference (Da R2019b)
minibatchpredictMini-batched neural network prediction (Da R2024a)
scores2labelConvert prediction scores to labels (Da 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