I started with the most basic course on Machine Learning at IIT Bombay. The course was a relatively beginner level course and was focused on basic Machine Learning algorithms and the underlying Mathematics behind them. For instance, I learned about Linear Regression, Logistic Regression, Support Vector Machines and basics of Neural Networks.
Later, I took which is certainly a great course to get started with ML. The course is a good mix of Algorithms + the Mathematics. The only downside is that it uses Octave as the programming language which obviously is something not very popular.
After that, I studied deeper level details from books like Bishop’s Pattern Recognition and Machine Learning. Reading books is always a great idea, particularly when you want to dive deep into a subject. The book is highly detailed and you may want to read only specific portions which you are interested in - at least, that’s what I did.
Subsequently, I focused on building stuff. The best way to learn something is to take up a couple of hands-on projects which teach you the concept end-to-end. Not only the projects are useful in learning, but also, they look great on the resume. For this, I took . The course is great for those who want to focus on applied Machine Learning rather than just the theory portion.
Learning ML is like learning how to swim. You can never learn it by reading stuff. To actually develop skills in ML, focus on applying it and you will surely be a master at it.