吴恩达关于如何阅读论文建议

Stanford CS230: Deep Learning | Autumn 2018 | Lecture 8 - Career Advice / Reading Research Papers - YouTube

主题阅读

• 收集资料

• 列出一个 list ，标注阅读进度。挑选有价值的论文阅读。

• 5-20 初步了解

• 50-100 很好理解前沿工作

如何阅读论文

多遍阅读策略

• 第一遍 :<-> 标题，摘要，图片

• 第二遍 :<-> 简介、结论、图片相关材料

• 第三遍 :<-> 进入论文主体部分，但是可以跳过数学，明白每个参数的含义。

• 第四遍 :<-> 阅读整篇文章，跳过没意义的部分(内容过时，没有火起来过)。
  阅读时思考的问题

• 1. 作者试图解决什么问题？
• 2. 研究方法的关键是什么？（最具有开创性）
• 3. 哪些东西可以为你所用？
• 4. 有哪些参考文献可以继续跟进？

读论文的延续性

• 在接下来一年保证每周读两篇文章比在一个月集中阅读50篇就更加行之有效。

How You Should Read Research Papers According To Andrew Ng (Stanford Deep Learning Lectures) | by Richmond Alake | Jul, 2020 | Towards Data Science

• In your first pass, start with reading the following sections within the paper: title, abstract and figures.

• The second pass entails you reading the following sections: introduction, conclusion, another pass through figures and scan through the rest of the content.

• The third pass of the paper involves reading the whole sections within the paper but skipping any complicated maths or technique formulations that might be alien to you. During this pass, you can also skip any terms and terminologies that you do not understand or aren’t familiar.

• Those conducting in-depth research into a domain can take a few more passes. These additional passes will mainly be focused on an understanding of the maths, techniques and unknown terminologies presented within the paper.