Deep learning uses neural networks to learn useful representations of features directly from data. Perform supervised learning with series and directed acyclic graph (DAG) convolutional neural networks (CNNs or ConvNets) for classification and regression. In addition to creating and training a new network, Neural Network Toolbox™ enables you to perform transfer learning using pretrained networks for image classification.
To get started, see Deep Learning in MATLAB.
Deep learning uses neural networks to learn useful representations of features directly from data. If you have labeled data, perform supervised learning with convolutional neural networks (CNNs, ConvNets) for classification, regression, and transfer learning using pretrained networks.
You can train a convolutional neural network on either a CPU, a GPU, or
multiple GPUs and/or in parallel. Training on a GPU or in parallel requires
Computing Toolbox™. Using a GPU requires a CUDA® enabled NVIDIA® GPU with compute capability 3.0 or higher. Specify the
training parameters including the execution environment using the
To learn more about
Convolutional Neural Network
Discover deep learning capabilities in MATLAB® using convolutional neural networks for classification and regression, including pretrained networks and transfer learning, and training on GPUs, CPUs, clusters, and clouds.
This example shows how to use transfer learning to retrain AlexNet, a pretrained convolutional neural network, to classify a new set of images.
Learn how to download and use pretrained convolutional neural networks for classification, transfer learning and feature extraction.
An introduction to convolutional neural networks and how they work in MATLAB.
This example shows how to create and train a simple convolutional neural network for deep learning classification.
Train deep networks on CPUs, GPUs, clusters, and clouds, and tune options to suit your hardware.