Main Content

Neural Networks

Neural networks for binary and multiclass classification

Neural network models are structured as a series of layers that reflect the way the brain processes information. The neural network classifiers available in Statistics and Machine Learning Toolbox™ are fully connected, feedforward neural networks for which you can adjust the size of the fully connected layers and change the activation functions of the layers.

To train a neural network classification model, use the Classification Learner app. For greater flexibility, train a neural network classifier using fitcnet in the command-line interface. After training, you can classify new data by passing the model and the new predictor data to predict.

If you want to create more complex deep learning networks and have Deep Learning Toolbox™, you can try the Deep Network Designer (Deep Learning Toolbox) app.


Classification LearnerTrain models to classify data using supervised machine learning


expand all

fitcnetTrain neural network classification model
compactReduce size of machine learning model
crossvalCross-validate machine learning model
kfoldLossClassification loss for cross-validated classification model
kfoldPredictClassify observations in cross-validated classification model
kfoldEdgeClassification edge for cross-validated classification model
kfoldMarginClassification margins for cross-validated classification model
kfoldfunCross-validate function for classification
lossClassification loss for neural network classifier
resubLossResubstitution classification loss
edgeClassification edge for neural network classifier
marginClassification margins for neural network classifier
resubEdgeResubstitution classification edge
resubMarginResubstitution classification margin
predictClassify observations using neural network classifier
resubPredictClassify training data using trained classifier


ClassificationNeuralNetworkNeural network model for classification
CompactClassificationNeuralNetworkCompact neural network model for classification
ClassificationPartitionedModelCross-validated classification model


Assess Neural Network Classifier Performance

Use fitcnet to create a feedforward neural network classifier with fully connected layers, and assess the performance of the model on test data.

Train Neural Network Classifiers Using Classification Learner App

Create and compare neural network classifiers, and export trained models to make predictions for new data.