Timeline for Training loss goes down and up again. What is happening?
Current License: CC BY-SA 3.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jan 30, 2018 at 15:10 | comment | added | n1k31t4 | As the OP was using Keras, another option to make slightly more sophisticated learning rate updates would be to use a callback like ReduceLROnPlateau, which reduces the learning rate once the validation loss hasn't improved for a given number of epochs. | |
| Jun 10, 2017 at 21:06 | history | edited | itdxer | CC BY-SA 3.0 |
added 5 characters in body
|
| Apr 8, 2016 at 13:21 | vote | accept | patapouf_ai | ||
| Apr 8, 2016 at 12:28 | history | edited | itdxer | CC BY-SA 3.0 |
edited body
|
| Apr 8, 2016 at 12:20 | history | answered | itdxer | CC BY-SA 3.0 |