How to Read Papers in Deep Learning ?

ref:

• https://blog.usejournal.com/advice-on-building-a-machine-learning-career-and-reading-research-papers-by-prof-andrew-ng-f90ac99a0182
• 吴恩达斯坦福CS230第八讲：新手如何读论文，怎么找工作
  https://mp.weixin.qq.com/s/CZGny8jZR4_mehrvSM_pHw
• youtube :
  https://www.youtube.com/watch?v=SHTOI0KtZnU&list=PL2-dafEMk2A4kRa2qZWxSTAXE7Q0k4qjF&index=10

Paper Numbers

• 5–20 papers (in a field of choice, say speech recognition) => it may be probably enough knowledge for you to implement a speech recognition system, but maybe not enough to research or be at the cutting-edge.
• 50–100 papers => you probably have a very good understanding of the domain application (speech recognition).

How do you read one paper?

Don’t start reading the paper from the first to the last word. Instead, take multiple passes through the paper, here’s how to do it:

1. Read the Title, the abstract and the figures: by reading the title, abstract, the key network architecture figure, and maybe the experiments section, you will be able to get a general sense of the concepts in the paper. In deep learning, there are a lot of research papers where the entire paper is summarized in one or two figures without the need to go hardly through the text.
2. Read the introduction + conclusions + figures + skim the rest: the introduction, the conclusions and the abstract are the places where the author(s) try to summarize their work carefully to clarify for the reviewer why their paper should be accepted for publication.
   Also, skim the related work section (if possible), this section aims to highlight work done by others that somehow ties in with the author(s) work. Hence, it may be useful to read it but if you’re not familiar with the literature, it is sometimes very hard to understand.
3. Read the paper but skip the math.
4. Read the whole thing but skip the parts that don’t make sense: great research means we’re publishing things at the boundaries of our knowledge and understanding.
   He also explained that when you read papers (even the most influential ones), you’ll find maybe some parts that is much less used or it doesn’t make sense. Consequently, it’s fine if you read a paper and some of it doesn’t make sense (it’s not unusual), it’s okay to skim it initially. Unless, you’re trying to master it, then spend more time.

When you read a paper, try to answer the following questions:

• What did the author(s) try to accomplish?
• What were the key elements of the approach?
• What can you use yourself?
• What other references do you want to follow?

5. 看看别人对这篇文章的看法？对比一下自己的观点

6. 如果感兴趣，second pass: 尝试去理解并推导数学公式

7. 阅读实验部分，如果是感兴趣的文章，不妨clone source code，跑一跑实验，对于有价值的代码，可以阅读代码后独立reimplement整个实验