I mean yes, but without knowing the maths then knowing how to optimize the maths is a bit useless?
At the very least you should know enough linear algebra that you understand scalar, vector and matrix operations against each of the others. You don't need to be able to derive back prop from first principles, but you should know what happens when you multiply a matrix by a vector and apply a non-linear function to the result.
Thanks! Yeah I do know some Math. I'm not sure how much I need to know. I guess the more the merrier, but it would be nice to know a line that I don't need to cross to properly do my job.
It's a tough one, I've never seen a book that actually covers the _bare_ minimum of the maths you need for ML.
The little learner comes close but I'd only really suggest that to people who already know the maths because the presentation is very non-standard and can get very misleading.
If you're interested drop me a line on my profile email and I'll have a look at some numerical algebra books and papers to see what's out there.