Main Content

Neural Networks

Neural networks for regression

Neural network models are structured as a series of layers that reflect the way the brain processes information. The regression neural network models 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 regression neural network model, use the Regression Learner app. For greater flexibility, train a regression neural network model using fitrnet in the command-line interface. After training, you can predict responses for 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.


Regression LearnerTrain regression models to predict data using supervised machine learning


expand all

fitrnetTrain neural network regression model
compactReduce size of machine learning model
crossvalCross-validate machine learning model
kfoldLossLoss for cross-validated partitioned regression model
kfoldPredictPredict responses for observations in cross-validated regression model
kfoldfunCross-validate function for regression
lossLoss for regression neural network
resubLossResubstitution regression loss
predictPredict responses using regression neural network
resubPredictPredict responses for training data using trained regression model


RegressionNeuralNetworkNeural network model for regression
CompactRegressionNeuralNetworkCompact neural network model for regression
RegressionPartitionedModelCross-validated regression model


Assess Regression Neural Network Performance

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

Train Regression Neural Networks Using Regression Learner App

Create and compare regression neural networks, and export trained models to make predictions for new data.