I am a JavaScript developer looking to expand my skills into AI and machine learning (ML). However, my research online has left me feeling confused due to the overwhelming number of courses, books, and resources available. I’m uncertain about where to begin and what to prioritize. In my professional network, I’ve received mixed advice. Some recommend starting with Andrew Ng's course on Coursera, while others suggest skipping it entirely.<p>To clarify my inquiry, I’d like to break it down into two parts:<p><pre><code> 1. Applied ML: What should I focus on when it comes to integrating machine learning into products?
2. Theoretical ML: What should I prioritize regarding the theoretical or research aspects of machine learning?
</code></pre>
So far, I have shortlisted two O'Reilly books[1][2] for the applied part.<p>For the theoretical part, I’m considering the fast.ai course[3]<p>Is this a good starting point, or is there a better approach I could take?<p>[1] Hands on LLM - https://learning.oreilly.com/library/view/hands-on-large-language/9781098150952/<p>[2] Applied machine learning and ai for engineers - https://learning.oreilly.com/library/view/applied-machine-learning/9781492098041/<p>[3] https://course.fast.ai/
I've only quickly skimmed the course on fast.ai and it seems to me that it has a more practical approach. It also says that math is not really important and high school math should do, which i do not agree with unless you only care about how to implement different techniques and hope for the best.<p>To understand the subject properly, I would say that you actually need a bit of a mathematical background to be able to understand the whys and hows of ML and DL.
For this, I would start with Elements of Statistical Learning [1] to get all the background.<p>After that, probably Andew NG's Coursera Course gives you the next steps and also how to implement all those methods. Maybe in the meantime there are better courses, but I'm not sure, I haven't looked into it in a long time.<p>The Deep Learning book [2] is good to get you started on all the classic DL methods, but won't really cover anything new (like vene transformers which by now are not even new anymore).<p>After that, you can probably start looking into trying out projects by yourself, even going on arXiv to check out newer research and familiarize yourself with the academical lingo and way to describe the maths and practicalities (imo could be way better, but academics have a big ego they cannot leave to deflate).<p>Also, might be important to mention that this whole thing set up like this, and made properly would take 1+ years with bachelor's knowledge already, so if you just want some basic knowledge, you could skim through some of those, but this would be the path I would recommend to get proper knowledge of all the bases, and fully understand what's happening in the field.<p>[1] <a href="https://hastie.su.domains/Papers/ESLII.pdf" rel="nofollow">https://hastie.su.domains/Papers/ESLII.pdf</a><p>[2] <a href="https://www.deeplearningbook.org/front_matter.pdf" rel="nofollow">https://www.deeplearningbook.org/front_matter.pdf</a>
FastAI course for 1, the Little Book of Deep Learning [0] / Deep Learning (Goodfellow et al) / the entire set of Kevin Murphy textbooks for 2 (in order of detail)<p>[0] <a href="https://fleuret.org/francois/lbdl.html" rel="nofollow">https://fleuret.org/francois/lbdl.html</a>