Neural Network Toolbox

Create, train, and simulate neural networks

Neural Network Toolbox™ provides algorithms, functions, and apps to create, train, visualize, and simulate neural networks. You can perform classification, regression, clustering, dimensionality reduction, time-series forecasting, and dynamic system modeling and control.

The toolbox includes convolutional neural network and autoencoder deep learning algorithms for image classification and feature learning tasks. To speed up training of large data sets, you can distribute computations and data across multicore processors, GPUs, and computer clusters using Parallel Computing Toolbox™.

Getting Started

Learn the basics of Neural Network Toolbox

Function Approximation and Nonlinear Regression

Create a neural network to generalize nonlinear relationships between example inputs and outputs

Pattern Recognition and Classification

Train a neural network to generalize from example inputs and their classes, construct a deep network using autoencoders

Deep Learning

Construct and train convolutional neural networks (CNNs, ConvNets) for classification and autoencoder neural networks for learning features


Discover natural distributions, categories, and category relationships

Time Series and Dynamic Systems

Model nonlinear dynamic systems; make predictions using sequential data

Neural Network Control Systems

Control nonlinear systems using model-predictive, NARMA-L2, and model-reference neural networks

Define Neural Network Architectures

Define new neural network architectures and algorithms for advanced applications