Not so much of a mystery:
There was no notable decrease in the mean AUROC, even when 95% of the least important areas of the image – those not including the optic disc – were removed.
So we know that it relates to the optic disc.
Comment on AI-screened eye pics diagnose childhood autism with 100% accuracy
Lmaydev@programming.dev 9 months agoA big problem with this type of ai is they are a black box.
We don’t know what they are identifying. We give it input and it gives output. What exactly is going on internally is a mystery.
Not so much of a mystery:
There was no notable decrease in the mean AUROC, even when 95% of the least important areas of the image – those not including the optic disc – were removed.
So we know that it relates to the optic disc.
partial_accumen@lemmy.world 9 months ago
Counterintuitively that’s also where the benefit comes from.
The reason most AI is powerful isn’t because its can think like humans, its because it doesn’t. It makes associations that humans don’t simply by consumption of massive amounts of data. We humans tell it “Here’s a bajillion sample examples of X. Okay, got it? Good. Now here’s 10 bajillion samples we don’t know if they are X or not. What do you, AI, think?”
AI isn’t really a causation machine, but instead a correlation machine. The AI output effectively says “This thing you gave me later has some similarities to the thing you gave me before. I don’t know if the similarities mean anything, but they ARE similarities”.
Its up to us humans to evaluate the answer AI gave us, and determine if the similarities it found are useful or just coincidental.
uriel238@lemmy.blahaj.zone 9 months ago
Incidentally to train AI, you need a bajillion samples of X and a bajillion-plus samples of not-X.
SpaceNoodle@lemmy.world 9 months ago
Sure, but if we could take the model generated by the AI and convert it into a set of quantifiable criteria - i.e., what is being correlated - we could use our human abilities of associative thought to gain an understanding of why this correlation may exist, possibly leading to better understanding of Autism overall.
Trainguyrom@reddthat.com 9 months ago
The problem is identifying what an AI model is doing is basically impossible. You can’t just decompile an AI model and see a bunch of logic, and you can’t view the machine code and reverse engineer it because it isn’t code in that sense. The best way to suss it out is to throw corner cases at it and try to figure out any common themes in the false negatives and false positives
SpaceNoodle@lemmy.world 9 months ago
No, we just haven’t come up with a way of reverse-engineering AI models yet.