Create, train, and simulate shallow and deep learning neural networks

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

Deep learning networks include convolutional neural networks (ConvNets, CNNs), directed acyclic graph (DAG) network topologies, and autoencoders for image classification, regression, and feature learning. For time-series classification and regression, the toolbox provides long short-term memory (LSTM) deep learning networks. You can visualize intermediate layers and activations, modify network architecture, and monitor training progress.

For small training sets, you can quickly apply deep learning by performing transfer learning with pretrained deep network models (including Inception-v3, ResNet-50, ResNet-101, GoogLeNet, AlexNet, VGG-16, and VGG-19) and models imported from TensorFlow™ Keras or Caffe.

To speed up training on large datasets, you can distribute computations and data across multicore processors and GPUs on the desktop (with Parallel Computing Toolbox™), or scale up to clusters and clouds, including Amazon EC2® P2, P3, and G3 GPU instances (with MATLAB® Distributed Computing Server™).

For a free, hands-on introduction to deep learning methods, see the Deep Learning Onramp.


Deep Learning Networks and Algorithms

Train CNNs, LSTM networks, and autoencoders for image classification, regression, and feature learning.

Learn more

Deep Learning Training, Pretrained Models, and Visualization

Perform transfer learning with pretrained deep network models and models from Keras and the Caffe Model Zoo.

Learn more

Accelerated Training with GPUs and Large Data Sets

Speed up neural network training and simulation of large data sets.

Learn more

Classification, Regression, and Clustering of Shallow Networks

Create, train, and simulate shallow neural networks.

Learn more

Shallow Network Architectures

Use a variety of supervised and unsupervised network architectures.

Learn more

Training Algorithms

Automatically adjust a shallow network's weights and biases using training and learning functions.

Learn more

Preprocessing, Postprocessing, and Improving Generalization

Improve the efficiency of shallow neural network training.

Learn more

Code Generation and Deployment

Deploy a trained network to production.

Learn more

Product Resources

Discover more about Neural Network Toolbox by exploring these resources.


Explore documentation for Neural Network Toolbox functions and features, including release notes and examples.


Browse the list of available Neural Network Toolbox functions.

System Requirements

View system requirements for the latest release of Neural Network Toolbox.

Technical Articles

View articles that demonstrate technical advantages of using Neural Network Toolbox.

User Stories

Read how Neural Network Toolbox is accelerating research and development in your industry.

Community and Support

Find answers to questions and explore troubleshooting resources.


Neural Network Toolbox apps enable you to quickly access common tasks through an interactive interface.

Try or Buy

Get a Free Trial

Test drive Neural Network Toolbox.

Get a trial

Ready to Buy?

Purchase Neural Network Toolbox and explore related products.

Contact sales
Pricing and licensing

Have Questions?


Contact Shounak Mitra,
Neural Network Toolbox Technical Expert

Email Shounak

Neural Network Toolbox requires: MATLAB

Related Solutions

Use Neural Network Toolbox to solve scientific and engineering challenges:

News and Events

Deep Learning with MATLAB