Timeline for How to get the mathematical expression of a trained network?
Current License: CC BY-SA 4.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Feb 22, 2023 at 21:16 | vote | accept | anderstood | ||
| Feb 22, 2023 at 20:12 | comment | added | Domen |
@anderstood, click on show all, then you can see expressions like MXNetLink`MXExecutorForward[...] ...
|
|
| Feb 22, 2023 at 20:06 | comment | added | anderstood |
I confirm that Domen answered exactly my question, and I also have differences in the order of $10^{-7}$. "Using Trace[trained[{1,2,3}]], you can see that the input is numerically transferred to MXNet" -> how do you read that in the output? I get essentially things like NeuralNetworksPrivateNetApply. Thank you by the way!
|
|
| Feb 22, 2023 at 19:44 | history | edited | Domen | CC BY-SA 4.0 |
added 65 characters in body
|
| Feb 22, 2023 at 19:34 | history | answered | Domen | CC BY-SA 4.0 |