Timeline for MLP for regression not learning enough?
Current License: CC BY-SA 4.0
15 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Nov 11, 2020 at 0:46 | vote | accept | Yassine Kebbati | ||
| Nov 11, 2020 at 0:46 | vote | accept | Yassine Kebbati | ||
| Nov 11, 2020 at 0:46 | |||||
| Oct 29, 2020 at 11:13 | comment | added | Dave | For completeness, the argument is that $4$ minimizes square loss, which is a common type of error to want to minimize (it what we minimize in OLS regression, for instance). | |
| Oct 29, 2020 at 11:10 | comment | added | Yassine Kebbati | Ok I see now why this isn't working ! Thank you | |
| Oct 29, 2020 at 11:02 | comment | added | Dave | Exactly, there is no relationship between the input and output variables. All you can use to predict your outputs is what you know about the outputs. (For instance, if you know that the mean of an output variable is 4, there is an argument to be made that, in the absence of any additional information, 4 is a good guess.) | |
| Oct 29, 2020 at 10:59 | comment | added | Yassine Kebbati | well I am trying to make an adaptive PID controller, where I have to adapt the three gains Kp, Ki, Kd based on the 5 inputs that affect the system to be controlled so I try many combinations of Kp, Ki, Kd using GA and optimize on that to create a dataset so that when applying the PID controller I can adapt the gains based those 5 inputs. So if there is no function that relates inputs to outputs the NN will not be able to learn right? | |
| Oct 29, 2020 at 10:54 | history | edited | Yassine Kebbati | CC BY-SA 4.0 |
added 57 characters in body
|
| Oct 29, 2020 at 10:48 | comment | added | Dave | I’m super curious why you want to write a regression between independent variables, though. | |
| Oct 29, 2020 at 10:42 | answer | added | Gijs | timeline score: 1 | |
| Oct 29, 2020 at 10:42 | answer | added | Dave | timeline score: 0 | |
| Oct 29, 2020 at 10:38 | comment | added | Dave | Please edit that important information into your original question. Not everyone reads comments. | |
| Oct 29, 2020 at 10:35 | comment | added | Yassine Kebbati | nope! I tried simpler ones and no luck , the data I use is generated through simulations I basically use genetic algorithms to optimize a control system under variable conditions so the data itself is random, so the inputs and outputs are not related | |
| Oct 29, 2020 at 10:34 | review | First posts | |||
| Oct 29, 2020 at 13:17 | |||||
| Oct 29, 2020 at 10:30 | comment | added | Dave | Have you had success with simpler models like linear regression? Do you have reason to believe that your variables will be predictive of the outcome? | |
| Oct 29, 2020 at 10:29 | history | asked | Yassine Kebbati | CC BY-SA 4.0 |