Timeline for Classification with noisy labels?
Current License: CC BY-SA 3.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 4, 2017 at 14:49 | comment | added | hunch | How is $\tilde{p}_t$ is equal to $0.3/N +0.7p_t$. If we take two class case then $\tilde{p}_t$ will be $Prob(\tilde{y} = +1|t) = 0.7Prob(y=+1|t) + 0.3Prob(y = -1|t)$. Similarly for $Prob(\tilde{y} = -1|t) = 0.7Prob(y=-1|t) + 0.3Prob(y = +1|t)$. Why $1/N$ term? Thanks | |
| Jun 21, 2016 at 10:23 | vote | accept | dontloo | ||
| Jun 20, 2016 at 3:49 | vote | accept | dontloo | ||
| Jun 20, 2016 at 8:03 | |||||
| Jun 13, 2016 at 16:09 | history | edited | Lucas | CC BY-SA 3.0 |
typo
|
| Jun 13, 2016 at 15:57 | history | answered | Lucas | CC BY-SA 3.0 |