Neural Net Pattern Recognition

Solve pattern recognition problem using two-layer feed-forward networks

Description

The Neural Net Pattern Recognition app lets you create, visualize, and train two-layer feed-forward networks to solve data classification problems.

Using this app, you can:

• Import data from file, the MATLAB^® workspace, or use one of the example data sets.

• Split data into training, validation, and test sets.

• Define and train a neural network.

• Evaluate network performance using cross-entropy error and misclassification error.

• Analyze results using visualization plots, such as confusion matrices and receiver operating characteristic curves.

• Generate MATLAB scripts to reproduce results and customize the training process.

• Generate functions suitable for deployment with MATLAB Compiler™ and MATLAB Coder™ tools, and export to Simulink^® for use with Simulink Coder.

Tip

To interactively build and visualize deep learning neural networks, use the Deep Network Designer app. For more information, see Get Started with Deep Network Designer.

×

Open the Neural Net Pattern Recognition App

• MATLAB Toolstrip: On the Apps tab, under Machine Learning and Deep Learning, click the app icon.

• MATLAB command prompt: Enter nprtool.

Examples

• Pattern Recognition with a Shallow Neural Network

Algorithms

The Neural Net Pattern Recognition app provides a built-in training algorithm that you can use to train your neural network.

Training Algorithm	Description
Scaled conjugate gradient backpropagation	Scaled conjugate gradient backpropagation updates weight and bias values according to the scaled conjugate gradient method. To implement this algorithm, the Neural Net Pattern Recognition app uses the trainscg function.