For fuck's sake,if you are teaching "Machine Learning For Developers",you don't have to waste a whole hour explaining what the fuck a variable is or what is an if statement.Developers know what that is....aaargh.Off to sleep.

Thats the problem with most online tutorials, lessons, etc. There is always a beginners part, which is like 25% of the course

This is why I study on my own, reading just official documentation, other peoples code, books, and practicing.

@Jase same

I have three words for you.

Washing Machine Learning

You'd be surprised. I'm on my final semester of CS Engineer, and 80% of the class don't know what's a variable, what's a field, what kind of memory management Java uses.

If that wasn't enough, they think that the variables in Haskell are the same that in Java...

Ok now people tell us which maching learning courses you suggest

Following.

I'd advise to rely on books and papers.I'll post my list here soon.The only online course i find worth it is Andrew Ngs on Cousera/Stanford Engineering.
Most courses are totally useless and only focus on Tensorflow and other libraries (Udacity courses in particular).Please don't use any material that uses only frameworks, that's why i suggest books.

@apex haskell doesn't have variables since they can't be modified.

BTW I'm on my sixth(out of eight) semester and I think most of my classmates know what a variable is lol.

@Luigi003 Sorry to burst your bubble, but Haskell DOES have variables, it's just that the context changes, because Haskell being a functional programming language it takes math concept of a variable, that's that "It's a variable that can take any value, but during evaluation time, it becomes a constant, until a result is given", or in other words, they're "immutable".

About my classmates not knowing what a variable is, it's about how some languages handle them (in memory, reference, scope, etc.)

@theScientist Great.I can say confidently now that i have a gist of what machine learning is all about.
Here is how my schedule is/was:

- Finished Andrew Ng's course.(cs229.stanford.edu).
- Took Prof. Yaser's Caltech course on Learning From Data.
- Read "Building Machine Learning Systems with Python". This is easy once you finished the first two it's more practical and necessary.
- Now am currently reading two books
1.Machine Learning: A Probabilistic Perspective
2.Pattern Recognition and Machine Learning.These are more theoretical and you can't start with them straight away.
Other materials i read intermittently:
- Berkley's Deconstructing Data Science : data8.org
- I am waiting for Dr. Fei Fei Li's CS231n lectures to be put online. : cs231n.github.io

This might not be comprehensive but it's what is working/worked for me.
PS.I also got my first Machine Learning freelance job( transcribing YouTube videos).
Happy reading and see you on the other side of the net.(neural net)😀

Nice! Keen to start learning this. 👌🏼

I learned ML and DL from books and NPTEL. I would definitely suggest mithesh khapras Deep learning from IIT Madras.