Timeline for What do we call something that assigns a weight to each case study which shows the importance of that case?
Current License: CC BY-SA 4.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 29, 2021 at 20:45 | comment | added | user137927 | Sure, thanks a lot for your time and suggestion. | |
| Mar 29, 2021 at 20:27 | comment | added | rajah9 | 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? | |
| Mar 29, 2021 at 19:23 | comment | added | user137927 | 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. | |
| Mar 29, 2021 at 19:10 | comment | added | rajah9 | 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. | |
| Mar 29, 2021 at 19:08 | comment | added | user137927 | 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. | |
| Mar 29, 2021 at 19:04 | history | answered | rajah9 | CC BY-SA 4.0 |