Orignal transformer paper "Attention is all you need" introduced by a layman | Shawn's ML Notes

  Рет қаралды 3,700

Yuxiang "Shawn" Wang

Yuxiang "Shawn" Wang

Ай бұрын

Thank you for checking out my video notes on the orignal transformer paper "Attention is all you need", as introduced by a layman - me! I would love to share my ML learning journey with you.
Paper information:
- Vaswani, Ashish, et al. "Attention is all you need." Advances in neural information processing systems 30 (2017).
Please let me know in the comment section regarding any questions, points of discussion, or anything you would like see next. See you in the next video!

Пікірлер: 16
@oo_wais
@oo_wais 23 күн бұрын
one of the very few videos i found on youtube that explains the architecture very well
@yuxiangwang9624
@yuxiangwang9624 23 күн бұрын
Thank you so much for the recognition!
@matthewritter1117
@matthewritter1117 17 күн бұрын
Incredible content and your style is a perfect mix of confident and relatable. Keep it up!
@yuxiangwang9624
@yuxiangwang9624 17 күн бұрын
I appreciate the encouragement :)
@tk-og4yk
@tk-og4yk Ай бұрын
Another Video! Looking forward to watching.
@yuxiangwang9624
@yuxiangwang9624 Ай бұрын
Haha thank you for your support! It was an old deck I made a year ago, so I might as well record it :)
@OEDzn
@OEDzn 29 күн бұрын
amazing video!
@yuxiangwang9624
@yuxiangwang9624 29 күн бұрын
Thank you!
@420_gunna
@420_gunna 28 күн бұрын
Seems like a great video, subbed! 🙂
@yuxiangwang9624
@yuxiangwang9624 28 күн бұрын
Thanks for the sub! Appreciate the recognition ❤️
@s8x.
@s8x. 29 күн бұрын
please do more videos like this
@yuxiangwang9624
@yuxiangwang9624 29 күн бұрын
Thank you! Will do :)
@isiisorisiaint
@isiisorisiaint 18 күн бұрын
pretty okay until andrew's attention slide, then when it comes to your own explanations things become murky, and when you get "explain" the decoder, and then the full codec, you're swiping everything under the rug in a few short seconds when in fact this is exactly the section you should have spent most of time. all in all, a nice video until adrew's slide, basically worthless afterwards
@yuxiangwang9624
@yuxiangwang9624 18 күн бұрын
Thanks for the feedback! Will learn to improve :) Would you mind explain in more details on which part I was missing for the encoder details? I can look into those and see if I can add some later!
@isiisorisiaint
@isiisorisiaint 8 күн бұрын
@@yuxiangwang9624 darn, i got a notification that you responded to my comment, but only the first line of your reply was shown ("Thanks for the feedback! Will learn to improve :)"), and i didn't actually open to see your full reply until now. I will be back to you with the details, sorry for the delay...
@MrMusk-it5nz
@MrMusk-it5nz 29 күн бұрын
You aren't definitely a layman
The math behind Attention: Keys, Queries, and Values matrices
36:16
Serrano.Academy
Рет қаралды 190 М.
MAMBA from Scratch: Neural Nets Better and Faster than Transformers
31:51
Algorithmic Simplicity
Рет қаралды 48 М.
Что будет с кроссовком?
00:35
Аришнев
Рет қаралды 2,5 МЛН
How to open a can? 🤪 lifehack
00:25
Mr.Clabik - Friends
Рет қаралды 10 МЛН
DINO -- Self-supervised ViT
11:18
Machine Learning Studio
Рет қаралды 12
Vision Transformer Basics
30:49
Samuel Albanie
Рет қаралды 15 М.
Prof. Chris Bishop's NEW Deep Learning Textbook!
1:23:00
Machine Learning Street Talk
Рет қаралды 71 М.
Transformers, explained: Understand the model behind GPT, BERT, and T5
9:11
Attention is all you need explained
13:56
Lucidate
Рет қаралды 77 М.
Transformer Neural Networks, ChatGPT's foundation, Clearly Explained!!!
36:15
StatQuest with Josh Starmer
Рет қаралды 539 М.
The Attention Mechanism in Large Language Models
21:02
Serrano.Academy
Рет қаралды 73 М.
[ 100k Special ] Transformers: Zero to Hero
3:34:41
CodeEmporium
Рет қаралды 34 М.
Опасная флешка 🤯
0:22
FATA MORGANA
Рет қаралды 698 М.
Samsung mobile phone waterproof display. samsung mobile phone digital s23ultra  #shorts
0:15