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

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!

[@oo_wais]

one of the very few videos i found on youtube that explains the architecture very well

[@yuxiangwang9624]

Thank you so much for the recognition!

[@tk-og4yk]

Another Video! Looking forward to watching.

[@yuxiangwang9624]

Haha thank you for your support! It was an old deck I made a year ago, so I might as well record it :)

[@matthewritter1117]

Incredible content and your style is a perfect mix of confident and relatable. Keep it up!

[@yuxiangwang9624]

I appreciate the encouragement :)

[@OEDzn]

amazing video!

[@yuxiangwang9624]

Thank you!

[@420_gunna]

Seems like a great video, subbed! 🙂

[@yuxiangwang9624]

Thanks for the sub! Appreciate the recognition ❤️

[@s8x.]

please do more videos like this

[@yuxiangwang9624]

Thank you! Will do :)

[@aga5979]

Thank you for the very valuable explanation. But in what f ucking world do laymen speak with dot product , cosine and e to the power of time and time prime? 😅😅😂😂.

[@isiisorisiaint]

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]

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]

@@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...

[@nxlamik1245]

Work on explainging things easily. It seems u have enough knowledw but you made it difficult

[@MrMusk-it5nz]

You aren't definitely a layman