What does HackerNews think of awesome-deep-learning-papers?
The most cited deep learning papers
Language:
TeX
#23
in
Deep learning
#26
in
Machine learning
Maybe one of the various Github "Awesome XYZ" lists that exists out there.
https://github.com/terryum/awesome-deep-learning-papers
https://endymecy.github.io/awesome-deeplearning-resources/
You might also track down the website for a DL class from a reputable university and mine the syllabus for a list of assigned readings. Do that for two or three such instances and you could probably come up with a pretty solid list.
Or may just ask Carmack to share the list he was referring to? Does anybody know if he responds to Tweets / Twitter DM's, etc?
EDIT:
Also, check out https://paperswithcode.com/
EDIT 2:
Also, not reading, but.. Andrej Karpathy has a Youtube channel now and has been putting up some videos on ML topics. Might be of interest?
You can start here:
https://github.com/terryum/awesome-deep-learning-papers
It would be nice if there was a readme for this repository. Like these AI and speaker recognition examples [1],[2].
I've been spending my free time getting myself familiar with ML and personally I'm focused on resharpening my math skills, reading papers from the "awesome deep learning papers" repo [1], playing with TensorFlow, and reading the Neural Networks and Deep Learning book [2]. I did my undergrad degree in math, so a lot of the math is just review for me, but ML seems to get fairly math heavy pretty quick. I would suggest anyone looking at ML to spend a good amount of time going through the backing math in addition to the CS parts, otherwise you might not develop much intuition for what's going on.