Timeline for Do Neural Networks suffer from high bias or high variance
Current License: CC BY-SA 4.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 19, 2021 at 16:47 | comment | added | seanv507 | Neural nets are initialised with weights close to zero, so you can say they start with high bias/low variance. stopped training again is a form of regularisation (bias decreases as you increase the number of training iterations. | |
| Mar 19, 2021 at 16:04 | answer | added | Igor F. | timeline score: 0 | |
| Sep 18, 2020 at 16:46 | vote | accept | Jack Armstrong | ||
| Sep 18, 2020 at 16:03 | answer | added | Akylas Stratigakos | timeline score: 3 | |
| Sep 18, 2020 at 0:09 | history | asked | Jack Armstrong | CC BY-SA 4.0 |