Timeline for Best practices for measuring and avoiding overfitting?
Current License: CC BY-SA 3.0
7 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jan 18, 2012 at 0:15 | vote | accept | B Seven | ||
| Sep 15, 2011 at 21:54 | history | tweeted | twitter.com/#!/StackStats/status/114457103627849730 | ||
| Sep 15, 2011 at 19:07 | comment | added | B Seven | OK, that makes sense. So different approaches to avoid overfitting work in different domains. | |
| Sep 15, 2011 at 12:58 | answer | added | Dikran Marsupial | timeline score: 6 | |
| Sep 15, 2011 at 12:35 | comment | added | richiemorrisroe | @ B Seven - if your validation set gets tainted (i assume by fitting models to it) then perhaps dividing your data into a training, test and validation set may be more appropriate? | |
| Sep 15, 2011 at 12:31 | comment | added | fabee | B Seven, your question is much too high level and not very specific. Basically the whole field of machine learning can be boiled down to the question of how to avoid overfitting. There are several strategies like cross-validation, regularization or using a proper prior. Every good machine learning book can help you with that (e.g. the Duda/Hart/Stork or the one by Bishop). It is also not clear what you mean by a "tainted validation set". If your model cannot cope with changing time series data, it means that it is probably too simple. But more complex models will need even more regularization. | |
| Sep 15, 2011 at 11:29 | history | asked | B Seven | CC BY-SA 3.0 |