Hacker News new | past | comments | ask | show | jobs | submit login

if the aim is to just read and understand the papers, it is just a matter of learning the ap calc and some first-year university maths to get the basics out of the way.

the rest of the journey is to find an ml course which acts like a survey of the current state of the art. this field has complexity due to abstraction and horrendous naming practices. to understand a given paper requires working your way in reverse from concepts around it.

in addition, learn a "maths in code" platform of your choice to map the concepts to something you can run.




I feeling like you described a “draw the rest of the owl” situation with “find an ml course”.

I’m basically in this situation, I’ve implemented products around AI and ML. I understand them at a practical level but want to dive into the theoreticals more. Finding a “survey ML course” is a huge challenge for me. I have absolutely no idea what’s considered state of the art.


i completely understand your point-of-view. tough to give a silver-bullet answer because things move so quickly.

i personally found this course to be a good place for deep learning (again not a survey course that covers classical ML for context) - https://uvadlc-notebooks.readthedocs.io/en/latest/index.html

however, the strategy that should give good results is going for the open-source coursework from one of the major universities. these courses may lag a semester or two from SOTA, but they often give a good overview. pick your poison and go from there. for example the above link was found the same way.




Join us for AI Startup School this June 16-17 in San Francisco!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: