Timeline for Validation accuracy less than training accuracy (with no sigh of overtraining)
Current License: CC BY-SA 4.0
2 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Sep 9, 2021 at 14:17 | comment | added | CakeMaster | Thank you for your response. Your answer makes sense. I will look more into my training and test/val data to see how they might differ from the training set. Yes, I am using the whole datasets for each epoch so that does explain the 'stair case' jumps. | |
| Sep 9, 2021 at 13:17 | history | answered | Edoardo Guerriero | CC BY-SA 4.0 |