Neural Network Toolbox

New Features

R2014b (Version 8.2.1) - Released 2 Oct 2014

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

See the Release Notes for details.

Previous Releases

R2014a (Version 8.2) - 6 Mar 2014

Version 8.2, part of Release 2014a, includes bug fixes.

See the Release Notes for details.

R2013b (Version 8.1) - 5 Sep 2013

Version 8.1, part of Release 2013b, includes the following enhancements:

  • Function code generation for application deployment of neural network simulation (using MATLAB Coder, MATLAB Compiler, and MATLAB Builder products)
  • Enhanced multi-timestep prediction for switching between open-loop and closed-loop modes with NARX and NAR neural networks
  • Cross-entropy performance measure for enhanced pattern recognition and classification accuracy
  • Softmax transfer function in output layer gives consistent class probabilities for pattern recognition and classification
  • Automated and periodic saving of intermediate results during neural network training

See the Release Notes for details.

R2013a (Version 8.0.1) - 7 Mar 2013

Version 8.0.1, part of Release 2013a, includes bug fixes.

See the Release Notes for details.

R2012b (Version 8.0) - 11 Sep 2012

Version 8.0, part of Release 2012b, includes the following enhancements:

  • Speed and memory efficiency enhancements for neural network training and simulation
  • Speedup of training and simulation with multicore processors and computer clusters using Parallel Computing Toolbox
  • GPU computing support for training and simulation on single and multiple GPUs using Parallel Computing Toolbox
  • Distributed training of large datasets on computer clusters using MATLAB Distributed Computing Server
  • Elliot sigmoid transfer function for faster simulation

See the Release Notes for details.