optbuild

Are the materials publicly available?

I am thinking something that teaches both theory and practical aspects.

I am talking about learning how to study a problem, model it properly and then design an end to end system.

Is it really possible to learn computer science and related math on your own with the help of books and building projects on your own? Assuming you have rudimentary programming knowledge in any imperative language like Python or C, etc.

I am aware of guides like teachyourselfCS for someone who is a developer or programmer already. But has anyone really benefited from those guides?

If you were in this kind of a situation which books and or hobby projects have really helped you?

Have you had any experience as a mediocre programmer where you coded mostly hit and miss style and then you did some project, read some book(s) or took some courses and you started to program like a scientific process and a mental model was formed and eventually became a good then a better programmer?

You started understanding programming languages much easier and better and were able to structure solutions in more elegantly and efficiently in code.

Suppose you have a wishlist of subjects or topics that you want to learn. And you primarily want to learn them by self study using books, videos, academic papers, etc.

What workflow or method do you follow to learn those subjects? Suppose you have varied interests not just on the superficial level. You want to go deep in studying and understanding those topics.

Do you study more than one subject at a time? Or do you intensely study one at a time? Do you write things down or make detailed notes?

How many topics and subjects have you studied that way?

Textbooks that really helped you learn the subject .

When anyone starts out in a new craft, even after grasping the fundamentals of the tools they are quite shaky and low on confidence until they have a significant experience in doing something that ultimately ramps up their confidence in their craftsmanship.

Similar things happen with novice programmers when they start out.

Then they read a beautiful codebase which they can fully understand and replicate, or build a project from scratch, or read a book or take a class on a subject. And their confidence is tremendously boosted thereafter.

What was it for you? How did you gain this confidence to take the first step from being a tinkerer to being a skilled craftman?

I want to learn machine learning, but, not in a hand wavy way. I want to go deep to understand and appreciate major works of the past, the present and future. Only way to do that is to understand the research papers and implement them on real datasets. For that I have to understand the math behind it.

I have calculus and some matrix algebra (not proof based linear algebra) background and I can program well.

Is there any guide equivalent to teachyourself CS but for machine learning and deep learning?

If not, then can you suggest open courses (preferably with assignments) or books from where I can learn both the required math and machine learning?

At what point in your life did you come across that book?