This is machine translation

Translated by Microsoft
Mouse over text to see original. Click the button below to return to the English verison of the page.

Pattern Recognition and Classification

Train a neural network to generalize from example inputs and their classes, construct a deep network using autoencoders


Neural Net Pattern Recognition Classify data by training a two-layer feed-forward network


Autoencoder Autoencoder class


nnstart Neural network getting started GUI
view View neural network
trainAutoencoder Train an autoencoder
trainSoftmaxLayer Train a softmax layer for classification
decode Decode encoded data
encode Encode input data
predict Reconstruct the inputs using trained autoencoder
stack Stack encoders from several autoencoders together
network Convert Autoencoder object into network object
patternnet Pattern recognition network
lvqnet Learning vector quantization neural network
train Train neural network
trainlm Levenberg-Marquardt backpropagation
trainbr Bayesian regularization backpropagation
trainscg Scaled conjugate gradient backpropagation
trainrp Resilient backpropagation
mse Mean squared normalized error performance function
regression Linear regression
roc Receiver operating characteristic
plotconfusion Plot classification confusion matrix
ploterrhist Plot error histogram
plotperform Plot network performance
plotregression Plot linear regression
plotroc Plot receiver operating characteristic
plottrainstate Plot training state values
crossentropy Neural network performance
genFunction Generate MATLAB function for simulating neural network

Examples and How To

Basic Design

Classify Patterns with a Neural Network

Use a neural network for classification.

Deploy Trained Neural Network Functions

Simulate and deploy trained neural networks using MATLAB® tools.

Deploy Training of Neural Networks

Use MATLAB Runtime to deploy functions that can train a model.

Training Scalability and Efficiency

Neural Networks with Parallel and GPU Computing

Use parallel and distributed computing to speed up neural network training and simulation and handle large data.

Automatically Save Checkpoints During Neural Network Training

Save intermediate results to protect the value of long training runs.

Optimal Solutions

Representing Unknown or Don't-Care Targets

Prevent unknown target values from impacting training.

Choose Neural Network Input-Output Processing Functions

Preprocess inputs and targets for more efficient training.

Configure Neural Network Inputs and Outputs

Learn how to manually configure the network before training using the configure function.

Divide Data for Optimal Neural Network Training

Use functions to divide the data into training, validation, and test sets.

Choose a Multilayer Neural Network Training Function

Comparison of training algorithms on different problem types.

Improve Neural Network Generalization and Avoid Overfitting

Learn methods to improve generalization and prevent overfitting.

Train Neural Networks with Error Weights

Learn how to use error weighting when training neural networks.

Normalize Errors of Multiple Outputs

Learn how to fit output elements with different ranges of values.

Deep Networks

Construct Deep Network Using Autoencoders

Illustration of using autoencoders to construct and train a deep network for image classification


Workflow for Neural Network Design

Learn the primary steps in a neural network design process.

Four Levels of Neural Network Design

Learn the different levels of using Neural Network Toolbox functionality.

Multilayer Neural Networks and Backpropagation Training

Workflow for designing a multilayer feedforward neural network for function fitting and pattern recognition.

Multilayer Neural Network Architecture

Learn the architecture of a multilayer neural network.

Understanding Neural Network Toolbox Data Structures

Learn how the format of input data structures affects the simulation of networks.

Neural Network Object Properties

Learn properties that define the basic features of a network.

Neural Network Subobject Properties

Learn properties that define network details such as inputs, layers, outputs, targets, biases, and weights.

Was this topic helpful?