Differences
This shows you the differences between two versions of the page.
| Both sides previous revisionPrevious revisionNext revision | Previous revisionLast revisionBoth sides next revision | ||
| data_mining:strategy [2018/05/21 17:16] – phreazer | data_mining:strategy [2018/05/21 17:31] – [Human level performance] phreazer | ||
|---|---|---|---|
| Line 43: | Line 43: | ||
| E.g. high quality images in dev/test set, user upload low quality images. => change metric and/or dev/test set | E.g. high quality images in dev/test set, user upload low quality images. => change metric and/or dev/test set | ||
| + | |||
| + | ====== Human level performance ====== | ||
| + | |||
| + | Bayes optimal error (best optimal error) | ||
| + | |||
| + | Human level error could be used as an estimate for Bayes error (e.g. in Computer Vision) | ||
| + | |||
| + | * H: 1%, Train: 8%, Dev: 10% => bias reduction | ||
| + | * H: 7,5%, Train: 8, Dev: 10% => variance reduction (more data, regularization) | ||
| + | |||
| + | What's human-level error? Best performance possible as a human / usefullness | ||
| + | |||
| + | Measure of error between Human Error, Train Error and Dev error | ||
| + | |||