Hi there! I’m having difficulty with the Machine Learning specialization – specifically, the jupyter notebooks. I’m a pretty humble guy, in terms of, I know my limits, and respect them, so that I can learn better. I’ve never written a line of python, nor have I ever taken one course in calculus. Needless to say, I can’t make heads or tails of these jupyter notebooks. Just got a 0 on the first graded jupyter notebook, which is to be expected. I guess I’m trying to figure out 1) how this is labeled as “For beginners”. I’ve taken high school algebra – this aint high school algebra. 2) how much knowledge do you really need to have prior to taking this specialization, because “for beginners” it is not. I’m a beginner, and this aint for me lol but I really want it to be for me.

Thank you very much for your response, which is helpful. I guess I’m just frustrated because I was really excited, and when it said high school math I was like “hey, I know high school math!” but I’m in this for the long haul, so on to the math specialization!

“Beginners” refers to your experience in machine learning - not your experience as a python programmer.

A note of caution - I do not recommend the Math for Machine Learning course very strongly - its presentation is inconsistent with almost everything you will see in other DLAI courses. This can cause a lot of confusion later.

It’s nice if you’re interested in math as a specialty, but you may not find it very useful in advancing your machine learning skills. For example, it spends a lot of time on topics that ML doesn’t really use (e.g. rolling loaded dice and solving systems of linear equations).

Heard on this… hmmm ok. I guess I just dont know where to go, then. I’m certain that I’m ready for content beyond “AI for Everyone” but I’m not quite ready for the Machine Learning Specialization, so where does that leave me, a true beginner? I’m learning python now in Mimo, but I’m curious about the actual math that A. Ng is referring to in the ML Spec – couldn’t make heads or tails of it. Is the math taught in the spec 100% irrelevant to what’s taught in the ML spec, or is it just that there’s some math that wont apply to ML specifically? Does deep learning AI have a recommended track/ sequential ordering for taking the courses?

The MLS courses don’t teach the math, they give you the equations and a rough description of what they do, and your job is to implement them in Python code.

So that’s where the “basic knowledge of algebra” comes in. All of the equations are simple algebra.

Implementing them in Python is the other challenge.

I went through the same path that you are describing, except I knew math. I did not know python at all. My existing linear algebra knowledge was not necessary. Python was. The process was VERY frustrating and VERY time consuming for me. I mean, it took me 40 hours to get through the first workbook. I got through it by sheer force of will and consider it one of my lifetime accomplishments. With that, here is my advice. Take an intro python course (where you learn things such as the fact an = sign has a different meaning than in math). Through that course, double down on the following concepts: data types, iterators, nested for loops, and the common procedure and associated nomenclature (ie., i, j, m, n) for iterating through lists and matrices, and also the vectorized approach using numpy functions. reach out if you have specific questions. Don’t bang your head against the wall, reach out.

Wow – thanks so much. I really, REALLY appreciate this. I’m very excited for AI, and the promise/ potential. And I do appreciate this community, and people like you, for reaching out and being welcoming. I want to do my part here, but developing a structure for my self-directed learning is proving to be a bit challenging. I will take your advice – thanks for showing me which aspects of Python to double-down on.