Learning: The training process.

      This process consists in a progressive adaptation of the synaptic connection values to let the NN learn the desired behavior. To achieve that goal we feed the NN with an input from training data, compare the NN's outputs with the training data's output; the differences are used to compute the (Least Mean Square) error of the NN's response. With an appropriate algorithm (like "back-propagation") its possible to retouch the synaptic weight values to reduce the error. The corrections must be done for all the training input-output sets many times or cycles.