logoalt Hacker News

amoorthy • yesterday at 9:18 PM • 1 reply • view on HN

Yes I saw 3Blue1Brown say the same thing in his tutorial on how neural nets worked where he built a simple model to recognize a particular letter. Good reminder.


Replies

rfgplk • yesterday at 9:22 PM

I've been dabbling with some of my own (tiny) models recently and it's actually shocking at what they can "learn" despite having _zero_ mention of it in it's training data.