[flatline]

If I recall, solving back propagation in multiple-layer perceptrons was an unsolved problem for some time, and the solution relies pretty much solely on partial differentiation. I don't know much about ML but things like neural networks were pure mathematical constructs before they were CS topics. I agree with the GP, though, you don't need to know the actual math for most of this stuff.

[disgruntledphd2]

On the point regarding the necessary knowledge of maths for ML (or indeed statistics which is the same material but a slightly different focus), I'm conflicted.

Coming at it from my perspective (learned a lot of math in high school, forgot most of it until I started a PhD), i would agree that a lot of the time, you don't need to understand the mathematical underpinnings of this stuff. That being said, as I've learned and remembered more of the math, my capability to understand (and debug errors) of all of this has increased tremendously.

I do think, if you intend to use ML every day, then you need to commit to understanding everything you use within a certain time frame of you beginning to use it (ideally immediately but that's often not possible). Anyway, derivatives are cool, and transform the way you look at the world, so you should definitely learn some of those.