Timeline for Fine Tuning vs Joint Training vs Feature Extraction
Current License: CC BY-SA 3.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jun 7, 2021 at 21:00 | comment | added | Edw590 | [Probably what I wrote is no longer useful for the OP, but for anyone else that might come across - if I'm correct in what I wrote, at least.] | |
| Jun 7, 2021 at 20:59 | comment | added | Edw590 | @Rafael If I'm not mistaken (I'm a beginner on neural networks), I think you may be confusing features with weights, which I believe are not the same thing. Features would be what the model detected as useful stuff from the input you provided it. Weights are what changes or not, which are one of the things used to generate the features (aside from activation functions, for example). Feature Extraction vs Fine-tunning in the middle of this page: learndatasci.com/tutorials/hands-on-transfer-learning-keras - it's helping me a lot to understand these concepts | |
| Jan 9, 2017 at 21:58 | comment | added | Rafael | I wonder why they call it feature extraction, better call it feature freezing. thanks for the explanation. | |
| Jan 9, 2017 at 21:57 | vote | accept | Rafael | ||
| Jan 9, 2017 at 21:19 | history | answered | Franck Dernoncourt | CC BY-SA 3.0 |