Timeline for Why are deep learning models unstable compare to machine learning models?
Current License: CC BY-SA 4.0
4 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Nov 26, 2021 at 12:21 | history | bounty ended | Kyv | ||
| Nov 20, 2021 at 18:38 | comment | added | Kyv | Thank you for these answers. I was just thinking about the initialization of the weights. But, I was a bit worried because the difference was very big every time I trained the same model with the same data. For example, training the deep learning model, gave 70% accuracy with perfect loss and accuracy functions. Then training the same model with the same data, and I got 50% accuracy with equally perfect functions. | |
| Nov 20, 2021 at 18:28 | vote | accept | Kyv | ||
| Nov 20, 2021 at 18:28 | |||||
| Nov 20, 2021 at 17:27 | history | answered | Brian Spiering | CC BY-SA 4.0 |