AForge.NET

Testimonials
Features
Samples
Tools
Documentation
License
Downloads
Sources
Discussions
Partners
Projects
Members
Donate

AForge.NET Framework
2.2.5 version is available!

Neural Networks Basics samples

Perceptron Classifier [Download]
Perceptron Classifier sample application

This sample application represents the very basics and the very beginning of neural network - single neuron with threshold function, which is knows as perceptron. The application demonstrates perception's usage and learning on the very simple tasks - classification of data belonging to 2 classes. Of course single perceptron can not solve a lot - it may just classify data, which are linearly separable. This allows to train it for AND or OR functions. But does not allow to train it for XOR function, which represents none linearly separable case.

One-Layer Perceptron Classifier [Download]
One-Layer Perceptron Classifier sample application

This sample application is similar to the above one, but it demonstrates classification of more data classes (also all of them are linearly separable from the rest of data). To be able to classify more classes this application uses already a layer of perceptrons, but not a single one. The demonstrated simplest neural network has number of outputs equal to number of classes. For a given input the network sets one of its outputs to 1 and the rest of outputs to 0. The output with value set to 1 represents class of the value given to the network.

Delta Rule Learning [Download]
Delta Rule Learning sample application

This sample is similar to the above one - it also classifies linearly separable data into several classes, which means that this sample also demonstrates a layer of neurons. But this time neurons have continuous activation function, but not a threshold function, which enables usage of new learning algorithm known as delta rule learning.