complex systems designed by humans can be assumed to *have* an explanation because the humans had purposes we know we can understand. ML is just showing complex patterns that may not *have* what humans call an explanation.
-
-
This Tweet is unavailable.
-
Pointing out problems so that we can try to address them, in my view, is less fear inducing in the long run compared to ignoring the problems and inevitably running into them.
End of conversation
-
-
-
It isn't controversial. James Mickens covers this in his USENIX security keynote with humor and technical detailshttps://youtu.be/ajGX7odA87k?t=300 …
-
This Tweet is unavailable.
- Show replies
New conversation -
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.
