In a classification problem, an output unit's task is to output a strong signal if a case belongs to its class, and a weak signal if it doesn't. In other words, it is attempting to model a function that has magnitude one for parts of the pattern-space that contain its cases, and magnitude zero for other parts.
This is known as a discriminant function in pattern recognition problems. An ideal discriminant function could be said to have a plateau structure, where all points on the function are either at height zero or height one.
exerpt from... https://www.statsoft.com/textbook/neural-networks/#intro
I know nothing compared the the great Caro Lucas, but in my opinion ( or IMHO) the accuracy of any discriminant function is dependant on proving the validation of assumptions in correlation with estimation of probability of truth. This applies to life as in Neural Networks. Otherwise it becomes a Belief rather than a characteristic of Nature.