How to Read Deep Learning Paper as a Software Engineer

preview_player
Показать описание
Deep learning papers can look daunting to read.

Especially if you don't have a strong theoretical background in machine or deep learning.

Some papers can be so dense with jargon, formulas, and magical-looking results that you might feel you are missing 10 years' worth of background knowledge to even start looking at the title.

In this video, I’ll show you how I read most deep learning papers easily, even for new deep learning subfields.

# Table of Content
- Introduction: 0:00
- Step 1 Get External Context : 1:44
- Step 2 First Casual Read : 2:46
- Step 3 Fill External Gap : 3:56
- Step 4 Conceptual Understanding : 4:24
- Step 5 Code Deep Dive : 5:36
- Step 6 Method and Result Slow Walk : 6:13
- Step 7 Weird Gap Identification : 7:40
- Conclusion : 8:12

Enjoy everyone, btw I've used some of these footage from other Youtubers in the video:

----

----
Follow Me Online Here:

___

Have a great week! 👋
Рекомендации по теме
Комментарии
Автор

so much how time do you take for this process? are there research papers you wrestle with for weeks?

samson
Автор

This is phenomenal, can't wait to try this out !

davidlaidbiggestfan
Автор

Hey Yacine, really agree with your points here, they're excellently conveyed. Great new channel I've found!

futureshockpod
Автор

Another great fluid video on an effective process to make progress with research.

mamotivated
Автор

could you dive more into how you take notes for papers?

Also, Eric Jang has these questions for understanding any ML papers quickly

1. What are the inputs to the function approximator?
2. What are the outputs to the function approximator?
3. What loss supervises the output predictions? What assumptions about the world does this particular objective make?
4. Once trained, what is the model able to generalize to, in regards to input/output pairs it hasn’t seen before?
5. Are the claims in the paper falsifiable?

do you think its missing anything?

benxneo