Deep Learning Toolbox™ (formerly Neural Network Toolbox™) provides a framework for designing and implementing deep neural networks with algorithms, pretrained models, and apps. You can use convolutional neural networks (ConvNets, CNNs) and long short-term memory (LSTM) networks to perform classification and regression on image, time-series, and text data. You can build advanced network architectures such as generative adversarial networks (GANs) and Siamese networks using custom training loops, shared weights, and automatic differentiation. Apps and plots help you visualize activations, edit and analyze network architectures, and monitor training progress.
You can exchange models with TensorFlow™ and PyTorch through the ONNX™ format and import models from TensorFlow-Keras and Caffe. The toolbox supports transfer learning with a library of pretrained models (including NASNet, SqueezeNet, Inception-v3, and ResNet-101).
You can speed up training on a single- or multiple-GPU workstation (with Parallel Computing Toolbox™), or scale up to clusters and clouds, including NVIDIA GPU Cloud DGX systems and Amazon EC2® GPU instances (with MATLAB® Parallel Server™).
This example shows how to fine-tune a pretrained GoogLeNet network to classify a new collection of images.
Learn how to use deep learning to identify objects on a live webcam with the AlexNet pretrained network.
This example shows how to classify an image using the pretrained deep convolutional neural network GoogLeNet.
This example shows how to use transfer learning to retrain ResNet-18, a pretrained convolutional neural network, to classify a new set of images.
This example shows how to create and train a simple convolutional neural network for deep learning classification.
This example shows how to create a simple long short-term memory (LSTM) classification network.
Use apps and functions to design shallow neural networks for function fitting, pattern recognition, clustering, and time series analysis.
Deep Learning Onramp
This free, two-hour deep learning tutorial provides an interactive introduction to practical deep learning methods. You will learn to use deep learning techniques in MATLAB for image recognition.
Interactively Modify a Deep Learning Network for Transfer
Deep Network Designer is a point-and-click tool for creating or modifying deep neural networks. This video shows how to use the app in a transfer learning workflow. It demonstrates the ease with which you can use the tool to modify the last few layers in the imported network as opposed to modifying the layers in the command line. You can check the modified architecture for errors in connections and property assignments using a network analyzer.
Deep Learning with MATLAB: Deep Learning in 11 Lines of MATLAB Code
See how to use MATLAB, a simple webcam, and a deep neural network to identify objects in your surroundings.
Deep Learning with MATLAB: Transfer Learning in 10 Lines of MATLAB Code
Learn how to use transfer learning in MATLAB to re-train deep learning networks created by experts for your own data or task.