Timeline for Is it possible to train a neural network as new classes are given?
Current License: CC BY-SA 3.0
3 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| May 2, 2019 at 15:44 | comment | added | nbro | Transfer learning does not necessarily address the catastrophic forgetting problem, though with a small learning rate (and by freezing some weights) you may not forget previously learned knowledge. Transfer learning is good for speeding up training or when you have a small number of samples. See my answer. Your answer can be misleading, and people continue to upvote it (probably because "transfer learning" is just popular, when it does not emphasize certain important aspects). | |
| Sep 19, 2017 at 5:47 | vote | accept | Th3Nic3Guy | ||
| Sep 18, 2017 at 16:37 | history | answered | Maxim | CC BY-SA 3.0 |