Timeline for Batch Normalization decreasing model accuracy
Current License: CC BY-SA 3.0
4 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Apr 8, 2020 at 3:28 | comment | added | beelze-b | BatchNorm has a $\gamma$ and $\beta$ term that actually do not necessarily make this true. | |
| Feb 5, 2018 at 10:58 | comment | added | Lugi | You can get away with it if you have residual connections. | |
| Feb 2, 2018 at 1:32 | comment | added | Piyush Dugar | Thanks, lugi. It did work and it is converging faster . I wonder why at so many places its used before the activation function. | |
| Jan 31, 2018 at 11:07 | history | answered | Lugi | CC BY-SA 3.0 |