In case of supervised learning we presume a training group consisting of training designs and the corresponding correct output values we want to at the output neurons after the training. While the network has not finished training,i.e. providing it is creating wrong outputs, these output values are referred to as teaching input and that for every single neuron individually. Thus, for a neuron j with the faulty output oj,tj is the teaching input, which means that it is the correct or desired output for a training pattern p.