How to Understand ML Papers Quickly | Eric Jang
My ML mentees often ask me some variant of the question “how do you choose which papers to read from the deluge of publications flooding Arxiv every day?”
My ML mentees often ask me some variant of the question "how do you choose which papers to read from the deluge of publications flooding Arxiv every day?” The nice thing about reading most ML papers is that you can cut through the jargon by asking just five simple questions. I try to answer these questions as quickly as I can when skimming papers. 1) What are the inputs to the function approximator? E.g. a 224x224x3 RGB image with a single object roughly centered in the view. 2) What are the outputs to the function approximator? E.g. a 1000-long vector corresponding to the class of the input i
Explore this link on the map →related reading
- Eric Jang: How to Understand ML Papers Quicklyblog.evjang.com
- An Opinionated Guide to ML Researchjoschu.net
- Templates for machine learning research papers | Neel Guhaneelguha.github.io
- Just Ask for Generalization | Eric Jangevjang.com
- Highly Opinionated Advice on How to Write ML Papers — LessWronglesswrong.com
- how to read research papers, in 5 minutes. | writingmasonjwang.com
- How To Become A Mechanistic Interpretability Researcher — AI Alignment Forumalignmentforum.org
- deeplearningbook.org/contents/ml.htmldeeplearningbook.org
- An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2 — AI Alignment Forumalignmentforum.org
- A Course in Machine Learningciml.info
- How To Become A Mechanistic Interpretability Researcher — LessWronglesswrong.com
- Meta Learninglilianweng.github.io