Timeline for Is it possible to train a neural network as new classes are given?
Current License: CC BY-SA 4.0
7 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Nov 17, 2020 at 18:37 | comment | added | nbro | Given that you provided links for all approaches other than "transfer learning twice", you may also add a link to some implementation/paper that shows that approach. | |
| Nov 17, 2020 at 18:37 | history | edited | nbro | CC BY-SA 4.0 |
deleted 122 characters in body
|
| Nov 17, 2020 at 18:35 | comment | added | Farshid PirahanSiah | used the previous datasets of training and add new class to them and re train the model. | |
| Nov 17, 2020 at 18:34 | history | edited | Farshid PirahanSiah | CC BY-SA 4.0 |
added 453 characters in body
|
| Nov 10, 2020 at 10:00 | comment | added | nbro | What do you mean by "transfer learning twice"? Apart from that, your suggestions are more or less appropriate. | |
| Oct 19, 2020 at 9:20 | review | First posts | |||
| Oct 20, 2020 at 4:37 | |||||
| Oct 19, 2020 at 9:19 | history | answered | Farshid PirahanSiah | CC BY-SA 4.0 |