1

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.

Improve this question
12
  • 1
    What's wrong with "weighting"?
    – Cascabel_StandWithUkraine_
    Commented Mar 29, 2021 at 17:13
  • 1
    Isn’t it just a ranking (or weighting) algorithm?
    – Jim
    Commented Mar 29, 2021 at 17:29
  • 3
    I would call it a weighting network. It assigns a weight to its input. I don’t thing weighting here will be confused with training the network if that’s what you’re asking. Weighting usually is not about discovering the value of some intrinsic attribute but is assigning metadata, if you will, based on some external criteria a la multi-criteria decision making.
    – Jim
    Commented Mar 29, 2021 at 17:50
  • 1
    I have removed my VTC, and upvoted. However, I have a lot of doubts about the question. At least 3 users here have suggested "weighting" as an answer. The OP's English is proficient, but they seem to be unfamiliar with the usage.
    – Cascabel_StandWithUkraine_
    Commented Mar 29, 2021 at 18:33
  • 1
    Obviously, 'triaging' would work here, were it not for the conflict with the standard medical usage. [triage: to examine problems in order to decide which ones are the most serious and must be dealt with first] [CD]
    – Edwin Ashworth
    Commented Mar 29, 2021 at 18:42

3 Answers 3

Reset to default
2

It seems that your Neural Network (NN) is doing a ranking of the importance of the cases. Here, a rank is similar (if not identical) to the OP's concept of weight.

I searched on scholar.google.com for neural network ranking model and found quite a few hits.

A re-ranking model for dependency parser with recursive convolutional neural network. In this work, we address the problem to model all the nodes (words or phrases) in a dependency tree with the dense representations. We propose a recursive convolutional neural network (RCNN) architecture...

Neural Ranking Models with Weak Supervision. The reason may be the complexity of the ranking problem, as it is not obvious how to learn from queries and documents when no supervised signal is available. Hence, in this paper, we propose to train a neural ranking model using weak supervision, where labels are obtained automatically without human annotators or any external resources (e.g., click data).

So if you called your NN a ranking model, you would be understood by your target audience.

Improve this answer
5
  • Thanks for your answer. Actually, it is not ranking, since ranking is a discrete process but we are doing a continuous process which is weight assigning.
    – user137927
    Commented Mar 29, 2021 at 19:08
  • So can you take the output layer of weights and place the importance of the cases in deciles? And is there a monotonic direction in the weights (that is, higher weight means more valuable case)? I'm having some trouble understanding your input and output layers.
    – rajah9
    Commented Mar 29, 2021 at 19:10
  • Yes, it is a neural network that takes an input and puts weight on it in the output layer. And yes more weights means more valuable.
    – user137927
    Commented Mar 29, 2021 at 19:23
  • It seems to me that you should not call this a weight model because there would be confusion in the data scientists' minds between the output weight and the NN's hyperparameter weight. If your NN model has weights monotonically increasing as case value increases, then you have a strict rank ordering (whether a discrete or continuous process). Your output layer might instead be providing a rough ranking (say from 1 to 10, if deciles). But it quacks and walks like a ranking model. Would you please take a look at the NN ranking models at scholar.google.com and posit a better fit?
    – rajah9
    Commented Mar 29, 2021 at 20:27
  • Sure, thanks a lot for your time and suggestion.
    – user137927
    Commented Mar 29, 2021 at 20:45
1

You are seeking a novel usage, so answers will necessarily be to some extent a matter of opinion. However, they will probably be drawn from a limited range of words. I restrict my suggestions to three. Other folk may add to the list:

assessor = a person whose job is to officially say how much something (such as a property) is worth especially so that it can be taxed according to that value law : a person who knows a lot about a particular subject and whose job is to give advice about that subject to a judge or other court official : a person whose job is to officially say how well someone has done on a test, in a competition, etc.

Merriam Webster

monitor = to watch and check a situation carefully for a period of time in order to discover something about it {in your case, its weighting}

Cambridge

evaluator = someone whose job is to judge the quality, importance, amount, or value of something {in your case, its weighting}

Cambridge

In giving a name to the neural network code you might therefore choose to anthropomorphize it and describe it as the evaluator, the assessor or the monitor.

Improve this answer
0
0

Consider a scoring network, which assigns a score to each input

score (MWD)

5: to determine the merit of : GRADE

Improve this answer

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .