dont like the output? thats fine simply label the training data using your own schema and people can reference it no need to argue about these things "under the zerohp model im a blorp but by the government model im a class 3 taxbag" see how easy that ishttps://twitter.com/0x49fa98/status/1282384960352133120?s=19 …
-
-
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
adversarial genders exist
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
This Tweet is unavailable.
-
You want to remove pronouns from language?
End of conversation
-
-
-
Gender... for what purpose? No-one ever talks about the *use* of the category. Is it so hard to understand that you'd want to use different models for medicine, relationships, bathroom provision etc? Even in medicine, it depends on what you're talking about at that moment.
-
It's like, idk, planets. Is Ganymede a planet? Not by the commonly accepted definition. Should it be treated as one for the purposes of planetary science? Obviously. It has more in common with Mars or Terra than any of those have with Jupiter.
- Show replies
New conversation -
-
-
logistic regression as classifier *ducks*
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
This Tweet is unavailable.
-
but maybe linearly separable ?
- Show replies
-
-
-
you still have to set the output dimension as the number of genders and no one knows how many there are
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.