Simple Java Swing application written to present learning abilities of Neural Networks. Program uses a back propagation algorithm and provides a set of adjustable logic gates which can be used for the testing purposes.
Download
logicnn.zip
It is important that before testing the Neural Network it must be trained. Some training properties like number of hidden layers or learning (iteration) steps can be set on a separate tab.
On the next tab which is called “Network Trainer” it is possible to define so called training set which corresponds to the possible combination of inputs and generated outputs. Based on that set a given Neural Network will be trained.
In order to test the behavior of the Neural Network , a “Network Tester” tab should be chosen which enables us to define some input values and to ask the network about its prediction.
