Use the Rules module to apply rules to translate or preprocess your data before it is processed by the neural network.
For example, you can use two input variables to create the values for a third input variable. You may believe that if you combine the price of gold and IBM stock and the total is > 400, the economy is improving. You can translate this information into a new network input as follows:
You can also use the Rules module to post-process the network's predictions and classifications. For example, if your outputs are categories and in the range zero to one, and you want any value in column 1 greater than .5 to be true (1), your rule might be:
If column 1 > = .5, then column 1 = 1,
else column 1 = 0.
In this way you can set your own threshold, in this case .5, for determining when the pattern is included in an output category. There are many other uses of applying rules to output data.
For more information, see the Rules Detail module.