Version 11.0, part of Release 2017b, includes the following enhancements:

  • Directed Acyclic Graph (DAG) Networks: Create deep learning networks with more complex architecture to improve accuracy and use many popular pretrained models
  • Long Short-Term Memory (LSTM) Networks: Create deep learning networks with the LSTM recurrent neural network topology for time-series classification and prediction
  • Deep Learning Validation: Automatically validate network and stop training when validation metrics stop improving
  • Deep Learning Layer Definition: Define new layers with learnable parameters, and specify loss functions for classification and regression output layers
  • Deep Learning Training Plots: Monitor training progress with plots of accuracy, loss, validation metrics, and more
  • Deep Learning Image Preprocessing: Efficiently resize and augment image data for training
  • Bayesian Optimization of Deep Learning: Find optimal settings for training deep networks (Requires Statistics and Machine Learning Toolbox)

See the Release Notes for details.

Version 10.0, part of Release 2017a, includes the following enhancements:

  • Deep Learning for Regression: Train convolutional neural networks (also known as ConvNets, CNNs) for regression tasks
  • Pretrained Models: Transfer learning with pretrained CNN models AlexNet, VGG-16, and VGG-19, and import models from Caffe (including Caffe Model Zoo)
  • Deep Learning with Cloud Instances: Train convolutional neural networks using multiple GPUs in MATLAB and MATLAB Distributed Computing Server for Amazon EC2
  • Deep Learning with Multiple GPUs: Train convolutional neural networks on multiple GPUs on PCs (using Parallel Computing Toolbox) and clusters (using MATLAB Distributed Computing Server)
  • Deep Learning with CPUs: Train convolutional neural networks on CPUs as well as GPUs
  • Deep Learning Visualization: Visualize the features ConvNet has learned using deep dream and activations

See the Release Notes for details.

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.

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.

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.