I am writing a scientific paper. I have a neural network (assume it as a black box), which takes a case study (a patient, or any other type of data) as input, and provides a weight for the input case study that shows its importance between the other cases. I am wondering what I should call this black-box. I first called it a weighing network, but my friend said that weighing means measuring weight. In our case, the network is not measuring something which already exists, but it provides an appropriate weight for it. My other candidates are "weight-provider" and "weight-giver". Which one is more appropriate in this case? Any other suggestion is really welcome.