How to Read Deep Learning Paper as a Software Engineer

  Рет қаралды 6,159

Deep Learning with Yacine

Deep Learning with Yacine

Күн бұрын

Пікірлер: 16
@samson6707
@samson6707 3 ай бұрын
so much how time do you take for this process? are there research papers you wrestle with for weeks?
@deeplearningexplained
@deeplearningexplained 3 ай бұрын
It really depends on the goal. If I'm trying to understand it deeply enough to mechanistically understand how the methodology work, this can take a few days to a week. If I'm trying to reproduce the paper result to incorporate it within my own research project, I might wrestle with the thing for a full month. However, I don't do this process with all papers. That would be wasteful. I select which paper have high relevancy for myself and my lab by reading lots of them superficially, then I pin point a few that have disproportionate benefits.
@davidlaidbiggestfan
@davidlaidbiggestfan Ай бұрын
This is phenomenal , can't wait to try this out !
@deeplearningexplained
@deeplearningexplained Ай бұрын
Let me know how it goes!
@futureshockpod
@futureshockpod 3 ай бұрын
Hey Yacine, really agree with your points here, they're excellently conveyed. Great new channel I've found!
@deeplearningexplained
@deeplearningexplained 3 ай бұрын
I’m glad it was useful, welcome to the channel :)
@benxneo
@benxneo 3 ай бұрын
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?
@deeplearningexplained
@deeplearningexplained 3 ай бұрын
Yes for sure, I'll be doing a deep technical dive on Segment Anything architecture so I'll take the opportunity to document the process from start to finish. These 5 points are good and cover most of the ground. The one thing I would add before anything else is: "0. How would the model be used in a real-world setting?" If you have a solid answer to that question, you will be able to better understand the method section (1-4) and find critical flaws in the author's reasoning (5).
@mamotivated
@mamotivated Ай бұрын
Another great fluid video on an effective process to make progress with research.
@deeplearningexplained
@deeplearningexplained Ай бұрын
:) I’m glad it was useful!
@lucasrotsen4862
@lucasrotsen4862 3 ай бұрын
Amazing content, thanks for sharing!
@deeplearningexplained
@deeplearningexplained 3 ай бұрын
Glad you enjoyed it!
@elshazer
@elshazer 3 ай бұрын
thank you so much!!!
@deeplearningexplained
@deeplearningexplained 3 ай бұрын
You are very welcome!
@KeldonLee
@KeldonLee 3 ай бұрын
great for AI beginner
@deeplearningexplained
@deeplearningexplained 3 ай бұрын
:)
Which Cross Validation Method to Use in Machine Learning?
10:40
Deep Learning with Yacine
Рет қаралды 1,4 М.
How to Read Deep Learning Code?
15:03
Deep Learning with Yacine
Рет қаралды 3,2 М.
99.9% IMPOSSIBLE
00:24
STORROR
Рет қаралды 29 МЛН
If people acted like cats 🙀😹 LeoNata family #shorts
00:22
LeoNata Family
Рет қаралды 46 МЛН
How many people are in the changing room? #devil #lilith #funny #shorts
00:39
How To Read Research Papers Effectively | Prof. David Stuckler
9:43
Prof. David Stuckler
Рет қаралды 86 М.
Generative AI in a Nutshell - how to survive and thrive in the age of AI
17:57
Stop With Software Estimates
16:54
ThePrimeTime
Рет қаралды 148 М.
Using ML To Solve Problems For A Manufacturing Company
9:53
Richard Aragon
Рет қаралды 1,7 М.
How to Read Math in Deep Learning Paper?
27:17
Deep Learning with Yacine
Рет қаралды 90 М.
AI can't cross this line and we don't know why.
24:07
Welch Labs
Рет қаралды 1,4 МЛН
Learn Machine Learning Like a GENIUS and Not Waste Time
15:03
Infinite Codes
Рет қаралды 212 М.
Andrew Ng Machine Learning Career Advice
10:02
Jared Beckwith, R. EEG T.
Рет қаралды 110 М.
BEST WAY to read and understand code
17:24
The Cherno
Рет қаралды 166 М.
Coding Was HARD Until I Learned These 5 Things...
8:34
Elsa Scola
Рет қаралды 782 М.