News for hackers. Stuff that matters.
Re:Cats, Rats, A.I., Oh My [video] by amelius on Sunday June 16, 2019 @03:16PM (#20197326)
Yeah but it makes you wonder: is it genius, or is it just brute force pattern matching?

And what if he gets a new cat, or his cat switches to a different kind of prey?

From the outside, it might seem as if he is enslaved by his pet.

Re:Cats, Rats, A.I., Oh My [video] by keerthiko on Sunday June 16, 2019 @04:17PM (#20197654)
> From the outside, it might seem as if he is enslaved by his pet.

I don't see the issue, this is the explicit contract of having a cat for a pet.

Re:Cats, Rats, A.I., Oh My [video] by fisherjeff on Sunday June 16, 2019 @04:55PM (#20197833)
> explicit contract

I think many first-time cat slaves would disagree

Re:Cats, Rats, A.I., Oh My [video] by chris_st on Sunday June 16, 2019 @08:55PM (#20198948)
They'll learn.
Re:Cats, Rats, A.I., Oh My [video] by fisherjeff on Sunday June 16, 2019 @11:07PM (#20199513)
It took me all of maybe 20 minutes
Re:Cats, Rats, A.I., Oh My [video] by velcrovan on Sunday June 16, 2019 @04:54PM (#20197831)
Brute force pattern matching would be cataloguing all possible matching pixel patterns. The whole point of the ML approach is that with a comparatively few images (yes even 20k is comparatively few) the computer will correctly match pixel-sets it has never encountered before.
Re:Cats, Rats, A.I., Oh My [video] by amelius on Sunday June 16, 2019 @05:08PM (#20197905)
If your comparison function returns a float instead of a binary value, then you don't need to match against every possible image. Instead you just return how much each image is "similar" to the given image. A simple approach is to use cross correlation for the similarity.