News for hackers. Stuff that matters.

A comment on Researchers: Are we on the cusp of an ‘AI winter’?. Parent comment

Re:Researchers: Are we on the cusp of an ‘AI winter’? by tintor on Friday January 17, 2020 @06:39PM (#22080866)
Difference between 97% and 99.99% in perception is huge for autonomous driving purposes. 300x less likely to cause an accident.
[ Parent | on HN ]
Re:Researchers: Are we on the cusp of an ‘AI winter’? by stefan_ on Friday January 17, 2020 @08:47PM (#22081590)
Remember those performances are for very constrained, some might say artificial tasks of specifically image recognition into categories.

Your Tesla might be 99.99% in recognizing red lights but will continue to drive straight into paper boxes in its immediate path.

[ Parent | on HN ]
Re:Researchers: Are we on the cusp of an ‘AI winter’? by dpflan on Friday January 17, 2020 @10:17PM (#22082005)
Do you know of any good resources to learn more about this idea of the rate of improvement of perception per percentage point?
[ Parent | on HN ]
Re:Researchers: Are we on the cusp of an ‘AI winter’? by xyhopguy on Friday January 17, 2020 @10:52PM (#22082144)
https://en.wikipedia.org/wiki/Odds_ratio

odds of crash a => 97% => 3 / 100

odds of crash for b => 99.99% => 1 / 10000

improvement (odds ratio in this case) is then 300x = odds of crash for b / odds of crash for a

[ Parent | on HN ]
Re:Researchers: Are we on the cusp of an ‘AI winter’? by FartyMcFarter on Saturday January 18, 2020 @05:48AM (#22083674)
That may be true at a given moment, but how about time? I usually don't care about the probability that I'll crash within the next millisecond, but I do care about the probability that I'll crash over a whole trip.
[ Parent | on HN ]