Re:Why the Austin airport situation was so dangerous
by jhomedall on Wednesday February 08, 2023 @09:55AM
(#34708809)
That's useless in this case. You need to be able to prove that it will work with all inputs, and there are too many combinations of inputs to exhaustively enumerate.
[ Parent
| on HN ]
Re:Why the Austin airport situation was so dangerous
by zaarn on Wednesday February 08, 2023 @10:05AM
(#34708975)
That would be true of any software system we put into an airplane, yet we have deployed software into airplanes.
If your AI has linear / continuous output, testing it should be no different than any other software.
Re:Why the Austin airport situation was so dangerous
by jhomedall on Wednesday February 08, 2023 @12:13PM
(#34711188)
There is no way to determine that a non-trivial neural network won't drastically diverge in output due to small changes in input (eg one pixel attacks on image classifiers). This is true for all current models I know of.
Almost all neural network implementations have continuous outputs (ie the nodes in the output layer produce a value between 0 and 1). That doesn't change the above issue at all.
This is much less of an issue with traditional methods