在开始阅读论文并尝试提炼知识框架之前，我观看了吴恩达老师关于Reading Research Papers的课程，并将它作为Paper Reading这个系列的第0篇。纸上谈来终觉浅，绝知此事要躬行。

Summary for reading papers

  1. Compile list of papers(journal/conference + medium/blog posts);
  2. Skip around the list(choose the interesting one and go ahead… then choose a new one).
  • 5-20 papers in an area: basic understanding
  • 50-100 papers in an area: good understanding

Reading one paper

The bad way to read the paper is to go from the first word until the last word.

Take multiple passes through the paper:

  1. Read the title, abstract, figures;
  2. Read the intro, conclusions, figures, skim the rest.(skim or even skip related work);
  3. Read but just skip/skim the math;
  4. Read the whole thing but skip parts that don’t make sense;

Ask yourself some questions after you’ve read it

  1. What did the authors try to accomplish?
  2. What were the key elements of the approach?
  3. What can you use yourself?
  4. What other references do you want to follow？

References