Accelerating the pace of engineering and science

Neural Network Toolbox

Deep Learning with CPUs

Deep Learning with CPUs

Run trained CNNs to extract features, make predictions, and classify data on CPUs as well as GPUs

Deep Learning with Arbitrary Sized Images

Deep Learning with Arbitrary Sized Images

Run trained CNNs on images that are different sizes than those used for training

Performance

Performance

Train CNNs faster when using ImageDatastore object

Deploy Training of Models

Deploy Training of Models

Deploy training of a neural network model via MATLAB Compiler or MATLAB Compiler SDK

Latest Releases

R2016b (Version 9.1) - 14 Sep 2016

Version 9.1, part of Release 2016b, includes the following enhancements:

  • Deep Learning with CPUs: Run trained CNNs to extract features, make predictions, and classify data on CPUs as well as GPUs
  • Deep Learning with Arbitrary Sized Images: Run trained CNNs on images that are different sizes than those used for training
  • Performance: Train CNNs faster when using ImageDatastore object
  • Deploy Training of Models: Deploy training of a neural network model via MATLAB Compiler or MATLAB Compiler SDK

See the Release Notes for details.

R2016a (Version 9.0) - 3 Mar 2016

Version 9.0, part of Release 2016a, includes the following enhancements:

  • Deep Learning: Train deep convolutional neural networks with built-in GPU acceleration for image classification tasks (using Parallel Computing Toolbox)

See the Release Notes for details.

R2015b (Version 8.4) - 3 Sep 2015

Version 8.4, part of Release 2015b, includes the following enhancements:

  • Autoencoder neural networks for unsupervised learning of features using the trainAutoencoder function
  • Deep learning using the stack function for creating deep networks from autoencoders​
  • Improved speed and memory efficiency for training with Levenberg-Marquardt (trainlm) and Bayesian Regularization (trainbr) algorithms​

See the Release Notes for details.

R2015a (Version 8.3) - 5 Mar 2015

Version 8.3, part of Release 2015a, includes the following enhancements:

  • Progress update display for parallel training

See the Release Notes for details.

R2014b (Version 8.2.1) - 2 Oct 2014

Version 8.2.1, part of Release 2014b, includes bug fixes.

See the Release Notes for details.