Neural Network Toolbox
Neural Network Toolbox™ provides algorithms, pretrained models, and apps to create, train, visualize, and simulate both shallow and deep neural networks. You can perform classification, regression, clustering, dimensionality reduction, time-series forecasting, and dynamic system modeling and control.
Deep learning networks include convolutional neural networks (ConvNets, CNNs), directed acyclic graph (DAG) network topologies, and autoencoders for image classification, regression, and feature learning. For time-series classification and prediction, the toolbox provides long short-term memory (LSTM) deep learning networks. You can visualize intermediate layers and activations, modify network architecture, and monitor training progress.
For small training sets, you can quickly apply deep learning by performing transfer learning with pretrained deep network models (GoogLeNet, AlexNet, VGG16, and VGG19) and models from the Caffe Model Zoo.
To speed up training on large datasets, you can distribute computations and data across multicore processors and GPUs on the desktop (with Parallel Computing Toolbox™), or scale up to clusters and clouds, including Amazon EC2®P2 GPU实例(withMATLAB®Distributed Computing Server™).
开始
Learn the basics of Neural Network Toolbox
Deep Learning Basics
Discover deep learning capabilities in MATLAB using convolutional neural networks (ConvNets) for classification and regression
Deep Learning Image Classification
Use pretrained deep networks to quickly learn new tasks, perform transfer learning and fine-tune a network, or perform feature extraction
Deep Learning Training from Scratch
Create new deep networks for image classification and regression, including series, DAG, and LSTM networks, import from Caffe, or define your own layers
Deep Learning Tuning and Visualization
Plot training progress, assess accuracy and make predictions, tune deep network training options, visualize features learned by a network
Function Approximation and Clustering
Perform regression, classification, and clustering using shallow networks; unsupervised learning with autoencoders
Time Series and Control Systems
Model nonlinear dynamic systems using shallow networks; make predictions using sequential data.