I want to learn some machine learning / deep learning in my spare time, to understand algorithms like Google’s AlphaGo. I recently learned Julia and I’m wondering if there are good pedagogical introductions to ML without relying on Python, e.g. using Julia, C++, or in a language-neutral manner. My main language is Mathematica (as I do lots of symbolic math) so I’m not motivated to spend time with yet another dynamic language with a global interpreter lock, such as Python. (I did learn some basic Python 10 years ago, so understand basic things like dict, list comprehension, functions etc., but I never became proficient with it and never wrote a Python program with more than a few dozen lines.)
I’ve only seen a few lectures of it, but Andrew Ng’s Coursera course is pretty popular and language-independent (at least I didn’t see any language-specific stuff), and free. From what I’ve seen it does a good job conveying ideas in a pedagogical way, but doesn’t get too much into the details (which can be good or bad depending on what you’re looking for).
If you’re still looking to deepen your learning (pun, intended), check out
It’s not easy but it’s setup to go deeper than a MOOC, with instructional staff support.
Either way, it’s a great time to learn ML and starting with Julia makes it so much easier to link math to code.
I am finding this blog and the associated code repository to be very helpful for modeling time series using Flux: https://sdobber.github.io/