Timeline for is scaling data [0,1] necessary when batch normalization is used?
Current License: CC BY-SA 4.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| S Oct 16, 2020 at 14:26 | history | suggested | Blade | CC BY-SA 4.0 |
typo fixed
|
| Oct 16, 2020 at 13:34 | review | Suggested edits | |||
| S Oct 16, 2020 at 14:26 | |||||
| Jun 23, 2020 at 21:58 | comment | added | Imran | Yes, see the "Alternate to Data Preparation" section in machinelearningmastery.com/…. And if I remember correctly, Jeremy Howard also mentions this technique in the first edition of his Practical Deep Learning for Coders video series. | |
| Mar 15, 2020 at 7:04 | comment | added | Black Jack 21 | As a hack, can I use batch norm in the first layer of my network? I am feeling lazy to preprocess the input :P | |
| Feb 16, 2018 at 14:41 | history | edited | Imran | CC BY-SA 3.0 |
added 4 characters in body
|
| Feb 16, 2018 at 13:14 | history | answered | Imran | CC BY-SA 3.0 |