Input Node Interrogator

After a network is near its fully trained state, it is often useful to determine what inputs are important to a network’s output response. For each output node, a plot will be produced (or a viewed in tabular format if selecting this option under Info) showing the relative importance of each input on that particular output. Sensitivities are determined by cycling each input for all training patterns and computing the effect on the network’s output response. Please note, this method of computing sensitivity assumes that each input value is independent of all other inputs. For models where this is not true, some caution should be used when interpreting the results.