#πŸ”’ Math Skills for ML and Data Science

16 messages Β· Page 1 of 1 (latest)

primal nova
#

Everyone says something different about the math skills needed for ML, which ones do you actually need to learn and where can you find good resources (free)? And when should you start learning them, before or after learning the basics of ML?

I don't really get that.
Could anyone explain please.

pale pawnBOT
#

@primal nova

Python help channel opened

Remember to:

  • Ask your Python question, not if you can ask or if there's an expert who can help.
  • Show a code sample as text (rather than a screenshot) and the error message, if you've got one.
  • Explain what you expect to happen and what actually happens.

:warning: Do not pip install anything that isn't related to your question, especially if asked to over DMs.

dense timber
#

I think you can get a layman's understanding of ML (like through 3b1b videos) without much math at all. if you're talking about classical algorithms, I would say to have a decent handle on calc, linalg, and stats. I'm trying to find the ML textbook I had in college..

wild gull
#

Think of learning ML as learning how to drive, and learning math as learning how to fix a car.

Strictly speaking, you don't need to learn one to learn the other, but you'll be like a clueless driver that doesn't have any idea of what that noise coming from the engine compartment means or how to fix it.

If you want to have a good foundation for understanding the math behind neural networks, learn Linear Algebra and Fuzzy Logic.
For everything else related to ML, there's statistics & probability, calculus, maybe some Boolean Logic.

primal nova
wild gull
#

Nothing specific other than learn fuzzy logic after basic logic.
Basic Logic, Stats & Prob and Lin Alg are the easiest.

primal nova
#

Ok, I get that. Thanks!

primal nova
wild gull
#

No, other than some videos my college professors made during the pandemic.

primal nova
#

One last question: Do you recommend learn Math or the basics of ML first?

wild gull
#

Start learning ML, if they explain something you don't understand, study the math behind it.

#

For learning ML there's the HarvardX course and kaggle. Both free.

primal nova
#

Thank you for your help! That helps alot

#

!close

pale pawnBOT
#
Python help channel closed with !close

This help channel has been closed. Feel free to create a new post in #1035199133436354600. To maximize your chances of getting a response, check out this guide on asking good questions.