[vayarajesh]

I have been reading alot about Machine Learning and I want to get into the practical application of it. So I will begin with learning Mathematics and then some Machine learning code for training a basic model for NLP or Facial Recognition :)

Any suggestions on how to go about learning Mathematics requires for Machine Learning is more than welcome

[StClaire]

Assuming you know the basics of calculus: learn lots of linear algebra, lots of probability theory, mathematical statistics, and optimization.

But you don't have to wait to learn all the math to get going

[solipsism]

He wants to get into the practical application of machine learning, not machine learning theory.

This is a common mistake people new to the field make. You can be very successful by learning how to use machine learning frameworks, and that doesn't require lots of probability theory, mathematical statistics, and optimization. Not that it hurts.

vayarajesh, start using Tensorflow, you'll reach the ability to reason about problems to which machine learning can be applied, and how to apply it, much more quickly than starting by starting at the root of the tree of knowledge. You can always learn as much math as you want in order to dig as deeply as you want, but first get a sense of what you're dealing with.

[dojomouse]

++ this. The branches of maths that are relevant to ML are all pretty extensive, and you can do a huge amount of applied ML and understand the underlying theory while understanding only a fairly small subset of (for e.g.) probability theory.

Starting by learning the maths will mean you learn a lot of stuff which isn't directly relevant. Not the worst thing that could happen, but you'll be a hell of a lot more directed (even if you want to learn the theory - and I would recommend learning at least some) if you pick a decent ML course and learn the maths you bump into as you go.

http://cs231n.github.io/ is one of the best general hands-on introductions I've found. The TF tutorials are pretty good too if you just want to try some things out, but I predict that once you've worked your way through the TF tuts you'll still not really understand what's going on and will feel a bit like you just learned the magic words that made the black box dance some particular dances.

As for notation - https://en.wikipedia.org/wiki/List_of_mathematical_symbols is really good for when you stumble on something unfamiliar.

Good luck.

[vayarajesh]

@solipsism, I did try out the TensorFlow playground and they use lot of mathematical terms which I don't understand yet. Al though I like the idea of diving in and then learning the concepts which I come across to accomplish NLP or Facial Recognition. Thanks.

[solipsism]

Mathematical terms like what? Perhaps they could just be explained to you. Starting at the root and working your way up is a long, long path. And unnecessary if your interest is primarily in applying ML.

[vayarajesh]

I am just starting with Calculus. Currently I am only comfortable with linear algebra - rest all I am just starting to learn.

Do you recommend any good books or resources?

[tonyedgecombe]

I've been using https://www.amazon.co.uk/gp/product/1137031204 to relearn some maths I'd forgotten. Pretty good so far.

[jimnotgym]

I want to re-learn all the maths I have forgotten...