Comment by D-Machine
9 hours ago
Yeah, the notation and math concepts also all just first-year calculus (or analysis, more accurately) and stats (and the latter being only E for expectation). Literally just summation notation, blackboard bold R for the real numbers, double bars for norm / distance, and then max/min with subscript for the quantity being minimized.
Embarrassing to complain about notation so simple, and, frankly, if you can't understand math concepts and notation this basic, you simply can't meaningfully understand modern neural networks: without the math, all you are doing is substituting loose analogies and metaphor for understanding. This is clearly an article for people that want more than that.
The notation itself sucks and anyone taking pride in the ability to parse it is suffering from Stockholm syndrome. It's also one of the most annoying things to look up because search engines ignore the symbols. AI can explain it based on a screenshot now, but then we might as well go to AI for the entire thing and I'm starting to lean in that direction just to spite authors like OP. You're also connecting the syntax to understanding of the concepts which is the cherry on top of the math snobbery in this thread. If the blog had pseudo-code instead of 18th century scribbles, the HN crowd would at least not openly admit to any parts they don't understand, because it's implied that you can code when you post here - not so much that you give a flying f--- about math or really anything theoretical.