[ExI] Neural networks score higher than humans in reading and comprehension test

Dylan Distasio interzone at gmail.com
Tue Jan 16 19:55:49 UTC 2018


Sorry, to be more specific, in theory, adversarial attacks can be used to
game machine learning systems in a black hat hacking sort of way.  You
could trick the system into doing exactly what you want it to just by
feeding it bad data for ill gotten gain.

On Tue, Jan 16, 2018 at 1:48 PM, spike <spike66 at att.net> wrote:

>
>
>
>
>
> Wait what?  Exploiting for profit is a problem?  I thought that was the
> solution.
>
>
>
> spike
>
> _______________________________________________
> extropy-chat mailing list
> extropy-chat at lists.extropy.org
> http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.extropy.org/pipermail/extropy-chat/attachments/20180116/a03b580a/attachment.html>


More information about the extropy-chat mailing list