News for hackers. Stuff that matters.

makintunde

"None of that really matters though because AFAIK you can't prove a neural net has been trained "correctly" and doesn't contain errors."

Progress is being made in this area. Here is an "old" paper: https://arxiv.org/abs/1702.01135

Re:Ask HN: Resources to learn real analysis? on Saturday March 24, 2018 @02:45PM (#16668131)
I think a lot of responses here are forgetting that OP is an undergraduate student in an _Applied_ Mathematics course. "A Concise Introduction to Pure Mathematics" by Martin Liebeck would be my suggestion.