Timeline for Regarding the output layer's activation function for continuous action space problems
Current License: CC BY-SA 4.0
8 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| May 16, 2019 at 3:41 | history | rollback | SellaDev |
Rollback to Revision 1
|
|
| May 15, 2019 at 15:13 | history | edited | nbro | CC BY-SA 4.0 |
deleted 20 characters in body
|
| Mar 27, 2019 at 5:02 | comment | added | SellaDev | Sorry for the bad news, but if you want to excel in machine learning in general, there is no actual rule of thumb for everything (including sigmoid for binary classification, it is just widely used and not a rule of thumb ), you have to try to think freely and solve each problem on it's own. you are welcome. | |
| Mar 26, 2019 at 15:44 | comment | added | stefanbschneider | Ok, that's not the answer I was hoping for :D But thank you anyways! | |
| Mar 26, 2019 at 10:03 | comment | added | SellaDev | There is no rule of thumb, it totally depends on your own problem. But as a good practice, you might want to use a function that bounds the values in a realistic range according to the actions that you want to predict. | |
| Mar 26, 2019 at 8:37 | comment | added | stefanbschneider | What activation function did you use then? Are there rules of thumb which activation function to use for which use case? For example, in classification there's the rule to use sigmoid for binary classification and softmax for multi-class classification. | |
| Mar 25, 2019 at 17:00 | review | First posts | |||
| Mar 25, 2019 at 19:14 | |||||
| Mar 25, 2019 at 16:56 | history | answered | SellaDev | CC BY-SA 4.0 |