Timeline for Similar data,same net,different level of MSE loss?
Current License: CC BY-SA 3.0
8 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| May 24, 2017 at 15:28 | comment | added | xslittlegrass | @partida I think in this case min-max is better because you are using relu activation and you want to put most of the data in [0,1] to minimize saturation. | |
| May 24, 2017 at 15:26 | history | edited | xslittlegrass | CC BY-SA 3.0 |
added 38 characters in body
|
| May 24, 2017 at 1:55 | comment | added | partida | But I have question,is min-max normalization better than mean-std normalization in this problem? | |
| May 24, 2017 at 1:54 | comment | added | partida | Cool!!!!! It solve my problem.Converges much faster!!! | |
| May 24, 2017 at 1:54 | vote | accept | partida | ||
| May 23, 2017 at 16:50 | history | edited | xslittlegrass | CC BY-SA 3.0 |
deleted 18 characters in body
|
| May 23, 2017 at 15:31 | history | edited | xslittlegrass | CC BY-SA 3.0 |
added 12 characters in body
|
| May 23, 2017 at 15:26 | history | answered | xslittlegrass | CC BY-SA 3.0 |