[sausagefeet]

This could just be an expectation problem. I think most of these free courses have that 'Applied' stuck infront of them, ok, fine. But for my education I want rigor. I don't want to just know how to use something, I want to know how the guy who came up with it figured it out and I want to be bale to prove things about it. Not having to know what a derivative is does not fit this. I don't think it's a matter of the elite thinking only elite people can grok something like ML, it's a matter of that they expect the dirty details and are annoyed when they don't get it.

[noblethrasher]

I know ML and have a math degree; I don't see why you'd need to know what a derivative is. If anything, I think exposure to ML and functional programming before differential calculus could be beneficial since you'd better appreciate that differentiation is just one special application (no pun intended) of the concept of higher order functions.

[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.

[volodia]

Well for example take the least squares formula \theta = (X^T X)^{-1} X y. You derive that by setting a derivative to zero, and solving for \theta. If you don't know what a derivative is, then you're just using an equation that came out of nowhere and that you don't understand.

[restofus]

If you want to know how the guy came up with it , do you think someone taught him that or he delved into the topic deeper by himself and figured it out .The professor makes it clear that you can do the derivates if you know so I do not understand how the course would be better if that was given as a assignment. Also if the professor thought the same way why would he want to teach a class instead of working for a bigco or a research firm ?

[sausagefeet]

Of course the guy who came up with it taught himself, there was nobody to teach him. The point of a college is to speed a lot of this up, though, and tell you the results these people got and how and the implications. I think you're drawing a bigger contrast between what we said than I intended. I'm not saying that Applied courses are wrong or should not exist. I have taken several in my day because I just don't have the mental discipline to learn a lot of theory all the time. What I am saying is that I don't think really smart people complaining about not getting enough out of the course is not a matter of them thinking they are elite but that they just want more and don't see the point in wasting time on something that won't give it to them. My favorite classes in college were always the ones that required a lot of theory and a lot of rigor because it brought so much more together for me (even though I often didn't really understand it), I think a the elite you speak of probably have similar feelings.