Re:Use of artificial intelligence for image analysis in brea...
by yangl1996 on Thursday September 02, 2021 @02:27PM
(#28395571)
They could have said "35 out of 36" instead of putting some scary number like "94%".
[ Parent
| on HN ]
Re:Use of artificial intelligence for image analysis in brea...
by axiom92 on Thursday September 02, 2021 @02:44PM
(#28395786)
35 out of 36 will be scarier to most people. In behavioral psychology they call this "denominator neglect."
Re:Use of artificial intelligence for image analysis in brea...
by jszymborski on Thursday September 02, 2021 @02:55PM
(#28395903)
Right, but surely sample size matters.
Re:Use of artificial intelligence for image analysis in brea...
by cratermoon on Thursday September 02, 2021 @02:37PM
(#28395687)
I shortened the title to fit HN limits. Why do you think "34 out of 36 were wrong" is less scary than "94% were wrong"?
Re:Use of artificial intelligence for image analysis in brea...
by rhacker on Thursday September 02, 2021 @03:12PM
(#28396079)
Another way to think about that:
%99.99 of AIs lose chess against our best human player.
When in reality 1 AI consistently beats all Human players every time.
Re:Use of artificial intelligence for image analysis in brea...
by cratermoon on Thursday September 02, 2021 @03:16PM
(#28396141)
Only if you can go back and demonstrate that the 2 AIs that didn't fail are consistent and demonstrably correct. Otherwise they just got lucky.
Re:Use of artificial intelligence for image analysis in brea...
by yawnxyz on Thursday September 02, 2021 @03:56PM
(#28396593)
I think if they flipped it and said "Only 1 out of 36 AI systems evaluated was more accurate than ..." would have a higher impact
Re:Use of artificial intelligence for image analysis in brea...
by qweqwweqwe-90i on Thursday September 02, 2021 @02:35PM
(#28395666)
You mean 34/36
Re:Use of artificial intelligence for image analysis in brea...
by MattGaiser on Thursday September 02, 2021 @02:28PM
(#28395582)
Is that less scary?