Timeline for Testing multiple Classification models
Current License: CC BY-SA 3.0
2 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jan 6, 2016 at 9:55 | comment | added | Bernardo Aflalo | Good point @mbq, an independent test set can help to reduce this effect. Still, I wonder if there is any formal test that would give me the following: even though my best model found is 83%, given the size of validation/ test set, the number of classes and the number of models tested, there is 95% probability of this model to have accuracy between X and Y range. | |
| Jan 5, 2016 at 21:34 | history | answered | user88 | CC BY-SA 3.0 |