Timeline for What's the difference between multi label classification and fuzzy classification?
Current License: CC BY-SA 4.0
12 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 21, 2019 at 7:38 | comment | added | Curious | I think fuzzy classification means we believe the instance belongs to one class and find probability that instance belongs to class 1,2 ..n. So conceptually it represents a single label classifier. | |
| Apr 23, 2019 at 15:55 | history | edited | Esmailian | CC BY-SA 4.0 |
Explanation improved
|
| Apr 23, 2019 at 15:50 | vote | accept | DmytroSytro | ||
| Apr 23, 2019 at 15:50 | comment | added | DmytroSytro | Thank you! Still, it kind of confuses me that in fuzzy sets there should be limit on the sum of probabilities, so that sample can't belong to different sets with probability 1 for each set. As I understand it's the result of the truth function in fuzzy logic that can't assign sum of probabilities more than 1. | |
| Apr 23, 2019 at 15:31 | comment | added | Esmailian | @DmytroSytro I've added a section to explain when sum=1 restriction is useful. | |
| Apr 23, 2019 at 14:42 | history | edited | Esmailian | CC BY-SA 4.0 |
Explanation improved
|
| Apr 23, 2019 at 14:37 | history | edited | Esmailian | CC BY-SA 4.0 |
Explanation improved
|
| Apr 23, 2019 at 14:29 | comment | added | DmytroSytro | So, does it really matter for fuzzy set that sum of probabilities for all classes equals to 1? | |
| Apr 23, 2019 at 14:27 | comment | added | Esmailian | @DmytroSytro you are right I added another example. | |
| Apr 23, 2019 at 14:27 | history | edited | Esmailian | CC BY-SA 4.0 |
Explanation improved
|
| Apr 23, 2019 at 14:19 | comment | added | DmytroSytro | Hmm, but I thought that is the point of multi-label classification not to use softmax, because classes don't exclude each other. | |
| Apr 23, 2019 at 14:13 | history | answered | Esmailian | CC BY-SA 4.0 |