Mathematics, machine learning & data

HN's go-to recommendation for learning linear algebra intuition, repeatedly credited with making concepts click and complementing textbooks.

HN treats it as the best starting point for really understanding backprop and neural nets, because Karpathy explains the why with intuition and builds everything in code.

HN's default recommendation for understanding the Fourier transform intuitively; many say it was the explanation that made it click.

HN treats it as the standard first stop for learning neural networks, praised for making the math intuitive.

HN's go-to recommendation for colormap and color-perception questions; commenters call it funny, brief, clear and a favorite talk.

It is HN's most frequently recommended starting point for quantum computing because it avoids pop-science hand-waving and needs only basic linear algebra.

HN commenters send it as a short antidote to cynicism, showing long-term global progress and the shrinking gap between rich and poor countries.

HN repeatedly cites it as the definitive explanation of SwissTable, the design behind Abseil, Rust's hash map and Go's maps.