Self Attention in Transformer Neural Networks (with Code!)

[@CodeEmporium]

If you think I deserve it, please consider liking the video and subscribing for more content like this :)

[@tomoki-v6o]

do have any idea how transformers generates new data ?

[@15jorada]

You are amazing man! Of course you deserve it! You are building transformers from the ground up! That's insane!

[@vipinsou3170]

​@@tomoki-v6ousing decoder 😮😮😊

[@radityawaliulu]

yeah off course

[@marktahu2932]

I have learnt so much between yourself, ChatGPT, and Alexander & Ava Amini iat MIT 6.S191. Thank you all.

[@jeffrey5602]

What's important is that for every token generation step we always feed the whole sequence of previously generated tokens into the decoder, not just the last one. So you start with the token and generate now new token, then feed + into the decoder, so basically just appending the generated token to the sequence of decoder inputs. That might have not been clear in the video. Otherwise great work. Love your channel!

[@tonywang7933]

Thank you so much, I searched so many places, this is the first place finally have a nice person willing to spend time really dig in step by step. I'm going to value this channel as good as Fireship now.

[@CodeEmporium]

Thanks for the compliments and glad you are sticking around!

[@MaksymLeshchenko-d7k]

I usually don't write comments, but this channel really deserves one! Thank you so much for such a great tutorial. I watched your first video about Transformers and the Attention mechanism, which was really informative, but this one is even more detailed and useful.

[@CodeEmporium]

Thanks so much for the compliments! This is the first in a series of videos called “Transformers from scratch “. Hope you’ll check the rest of the playlist out

[@nikkilin4396]

It's one of the best videos I have watched. The concepts are explained very much, specially with codes.

[@shullepys]

I'm finally understanding self attention thanks to this video! Thank you!

[@softwine91]

What can I say, dude! God bless you This is the only content on the whole youtube that really explain the self-attention mechanism in a brilliant way. Thank you very much. I'd like to know if the key, query, and value matrixes are updated via backpropagation during the training phase.

[@CodeEmporium]

Thanks for the kind words. These matrices I mentioned in the code represent the actual data. So no. However, the 3 weight matrices that map a word vector to Q,K,V are indeed updated via backprop. Hope that lil nuance makes sense

[@picassoofai4061]

I definitely agree.

[@EngineeredFemale]

I was legit searching for self attention concept vids and thinking that it sucked that you didn't cover it yet. And voila here we are. Thankyou so much for uploading!!

[@CodeEmporium]

Glad I could deliver. Will be uploading more such content shortly :)

[@simonebonato5881]

One video to understand them all! Dude thanks I've tried to watch like 10 other videos on transformers and attention, yours was really super clear and much more intuitive!

[@CodeEmporium]

Thanks so much for this compliment! Means a lot :)

[@rainmaker5199]

This is great! I've been trying to learn attention but it's hard to get past the abstraction in a lot of the papers that mention it, much clearer this way!

[@rajpulapakura001]

This is exactly what I needed! Can't believe self-attention is that simple!

[@kotcraftchannelukraine6118]

I still not understand how to perform a backward pass on the self-attention

[@muskanmahajan04]

The best explaination on the internet, thank you!

[@CodeEmporium]

Thanks so much for the comment. Glad you liked it :)

[@radityawaliulu]

GREAT,, i hopeyou give more than one hour,, you explain it well than my lecture

[@srijeetful]

Extremely well explained. Kudos !!!!

[@becayebalde3820]

This is pure gold man! Transformers are complex but this video really gives me hope.

[@pratyushrao7979]

What are the prerequisites for this video? Do we need to know about encoder decoder architecture before hand? The video feels like I jumped right in the middle of something without any context. I'm confused

[@cv462-l4x]

​@pratyushrao7979 there are Playlists for different topics

[@arunganesan1559]

Thanks!

[@CodeEmporium]

Thanks for the donation! And you are very welcome!

[@shivamkaushik6637]

With all my heart, you deserve a lot of respect Thanks for the content. Damn I missed my metro station because of you.

[@CodeEmporium]

Hahahaha your words are too kind! Please check the rest of the Transformers from scratch” playlist for more (it’s fine to miss the metro for education lol)

[@shailajashukla5841]

Excellent , how well you explained. NO other video on youtube explained like this , Really done good job.

[@debjanidas5786]

search CampusX

[@jazonsamillano]

Great video. Thank you very much.

[@CodeEmporium]

Thanks so much!

[@dataflex4440]

This Has been a most wonderful series on this channel so far

[@CodeEmporium]

Thanks a ton! Super glad you enjoyed the series :D

[@varungowtham3002]

ನಮಸ್ಕಾರ ಅಜಯ್, ನೀವು ಕನ್ನಡಿಗ ಎಂದು ತಿಳಿದು ತುಂಬ ಸಂತೋಷವಾಯಿತು! ನಿಮ್ಮ ವಿಡಿಯೋಗಳು ತುಂಬ ಚನ್ನಾಗಿ ಮೂಡಿಬರುತ್ತಿವೆ.

[@CodeEmporium]

Glad you liked this and thanks for watching! :)

[@prashantlawhatre7007]

waiting for your future videos. This was amazing. especially the masked attention part.

[@CodeEmporium]

Thanks so much! Will be making more over the coming weeks

[@noahcasarotto-dinning1575]

Best video explaining this that ive seen by far

[@pranayrungta]

Your videos are way better than Stanford lecture cs224n

[@CodeEmporium]

Words I am not worthy of. Thank you :)

[@ayoghes2277]

Thanks a lot for making the video!! This deserves more views.

[@CodeEmporium]

Thanks for watching. Hope you enjoy the rest of the playlist as I code the entire transformer out !

[@pocco8388]

Best contents ever I've seen. Thanks for this video.

[@giovannibianco5996]

best video found about the topic, great

[@CodeEmporium]

Thanks a ton for watching

[@nexyboye5111]

thanks, this is the only video I found useful on attention.

[@Wesker-he9cx]

Bro You're The Best, Mad Respect For You, I'm Subscribing

[@MahirDaiyan7]

Great! This is exactly what I was looking for in all of the other videos of yours

[@CodeEmporium]

Thanks for the comment! There is more to come :)

[@junior14536]

My god, that was amazing, you have a gift my friend; Love from Brazil :D

[@CodeEmporium]

Thanks a ton :) Hope you enjoy the channel

[@ChrisCowherd]

Fantastic explanation! Wow! You have a new subscriber. :) Keep up the great work

[@lawrencemacquarienousagi789]

Wonderful works you've done! I really love your video and have studied twice. Thank you so much!

[@CodeEmporium]

Thanks so much for watching! More to come :)

[@JBoy340a]

Great walkthrough of the theory and then relating it to the code.

[@CodeEmporium]

Thanks so much! Will be making more of these over the coming weeks

[@ishwaragoudapatil9654]

Nice explanation. Thanks a lot Kannadiga :)

[@AI-xe4fg]

Good video Bro. Studying Transformer this week but still a little confused before I met your video. Thanks

[@CodeEmporium]

Thanks for the kind words. I really appreciate it :)

[@deepalisharma1327]

Thank you for making this concept so easy to understand. Can’t thank you enough 😊

[@CodeEmporium]

My pleasure. Thank you for watching

[@ganesha4281]

ನಮಸ್ಕಾರ ಅಜಯ್, ನೀವು ಕನ್ನಡಿಗ ಎಂದು ತಿಳಿದು ತುಂಬ ಸಂತೋಷವಾಯಿತು!

[@Slayer-dan]

Huge respect ❤️

[@CodeEmporium]

Thanks so much!

[@shaktisd]

Excellent video . If you can please make a hello world on self attention like first showing pca representation before self attention and after self attention to show how context impacts the overall embedding

[@nandiniloomba]

Thank you for teaching this.❤

[@CodeEmporium]

My pleasure! Hope you enjoy the series

[@chrisogonas]

Awesome! Well illustrated. Thanks

[@bradyshaffer3302]

Thank you for this very clear and helpful demonstration!

[@CodeEmporium]

You are so welcome! And be on the lookout for more :)

[@rajv4509]

Absolutely brilliant! Thumba chennagidhay :)

[@CodeEmporium]

Thanks a ton! Super glad you like this. I hope you like the rest of this series :)

[@PraveenHN-zj3ny]

very happy to see kannada here Great 😍Love from kannadigas

[@klam77]

"query" , "key" , and "value" terms come from the world of databases! So how do individual words in "My name is Ajay" each map to their own query and key and value semantically? that remains a bit foggy. i know you've shown random numbers in the example, but is there any semantic meaning to it? is this the "embeddings" of the LLM?

[@maximilianschlegel3216]

This is an incredible video, thank you!

[@CodeEmporium]

Thanks so much for watching and commenting!

[@bhavyageethika4560]

why is it d_k in both Q and K in the np.random.randn ?

[@PaulKinlan]

This is brilliant, I've been looking for a bit more hands on demonstration of how the process is structured.

[@CodeEmporium]

Thanks so much! Happy you liked it :)

[@Danpage04]

how do we actually choose the dimensions of Q, K and V? Also, are they parameters that are fixed for each word in the English language, and do we get them from training the model? That part is a little confusing since you just mentioned that Q, V and K are initialized at random, so I assume they have to change in the training of the model.

[@kotcraftchannelukraine6118]

Q - query, V - value and K - key

[@jamesjang8389]

Amazing video! Thank you😊😊

[@CodeEmporium]

You are very welcome

[@chessfreak8813]

Thanks! U r very deserved and underdog!

[@picassoofai4061]

Mashallah, man you are a rocket.

[@CodeEmporium]

Thanks for the kind words :)

[@prasadhadkar1775]

I have a question, since we generated q k and v randomly, how does the output that you are getting in your jupyter notebook have correct matrix values? like how is the value corresponding to my and name in matrix high, without any training?

[@elunsgrace]

Usually masking is done with the queries on columns and with keys as rows(attention pattern), so the masking matrix will be an upper triangular matrix of ones.Am I wrong here or can it be done this way also?

[@rameshsimhadri4884]

Here q,k,v are randomly generated. But they have to be generated by multiplying input embedding with Wq,Wk,Wv matrices. How these matrices are generated? What are the inputs and outputs to these matrices.

[@radityawaliulu]

8:34 how in formula you give + M? instead in journal doesnt belong +M.

[@mamo987]

Amazing work! Very glad I subscribed

[@CodeEmporium]

Thanks so much for commenting!

[@virtualphilosophyjourney8897]

which phase does the model take the pretrianed info to decide the output?

[@erfanemami1595]

Well explained!!!

[@rameshsimhadri4884]

Regarding advantage in transformer architecture over RNNs, that parallel processing is possible; However we are doing parallel processing in encoder but it is still sequential processing in decoder. May I request you to clarify?

[@sockmonkeyadam5414]

u have saved me. thank u.

[@ParthivShah]

Really Appreciate Your Efforts. Love from Gujarat India.

[@sriramayeshwanth9789]

you made me cry brother

[@imagiro1]

Got it, thank you very much, but one question: What I still don't understand: We are talking about neural networks, and they are trained. So all the math you show here, how do we (know|make sure) that it actually happens inside the network? You don't train specific regions of the NN to specific tasks (like calculating a dot product), right?

[@FelLoss0]

Dear Ajay. Thank you so much for your videos! I have a quick question here. Why did you transpose the values in the softmax function? Also... why did you specify axis=-1? I'm a newbie at this and I'd like to have strong and clear foundations. have a lovely weekend :D

[@faiazahsan6774]

Thank you for explaining in such an easy way. It would be great if you could upload some codes on GCN algorithm.

[@CodeEmporium]

I shall explore that possibility!

[@7_bairapraveen928]

why we need to stabilise the variance of attention vector with query and key vectors.

[@McMurchie]

Hi I noticed this has been added to the transformer playlist, but there are 2 unavailable tracks - do i need them in order to get the full end to end grasp?

[@CodeEmporium]

You can follow the order of “transformers from scratch” playlist. This should be the first video in the series. Hope this helps and thanks for watching ! (It’s still being created so you can follow along :) )

[@ritviktyagi9221]

How did we get the values of q, k and v vectors after initializing them as randoms. Great video btw. Waiting for more such videos.

[@CodeEmporium]

The weight matrices that map the original word vectors to these 3 vectors are trainable parameters. So they would be updated by back propagation during training

[@ritviktyagi9221]

@@CodeEmporium Thanks for clarification

[@paull923]

Thx for your efforts!

[@CodeEmporium]

Super welcome :)

[@dataflex4440]

Brilliant Mate

[@CodeEmporium]

Thanks a ton! :)

[@yijingcui7736]

this is very helpful

[@CodeEmporium]

Glad! And thank you!

[@yonahcitron226]

this is amazing!

[@CodeEmporium]

Thanks a lot!

[@gabrielnilo6101]

I stop the video sometimes and roll it back some seconds to hear you explaining something again and I am like: "No way that this works, this is insane", some explanations on AI techniques are not enough and yours are truly simple and easy to understand, thank you. Do you collab with anyone when making these videos, or is it done all by yourself?

[@CodeEmporium]

Haha yea. Things aren’t actually super complicated. :) I make these videos on my own. Scripting, coding, research, editing. Fun stuff

[@TechTrendSpectrum]

Sir, I have my assigment to write report on, " Large Language Model are few shot clinical information extractor" and I have to make such LLM,,, and I reach here to your video. Sir can you please guide me.? Always be thankful!

[@govindkatyura7485]

I have a few doubts 1. Do we use multiple ffnn after the attention layer? So suppose we have 100 input words for the encoder then 100 ffnn will get trained ? One for each of the word, i checked the source code but they were using only one, so I'm confused how one FFNN can handle multiple embedding specially with batch size. 2. In decoder do we pass multiple input also, just like encoder layer specially in training part?

[@pulkitmehta1795]

Simply wow..

[@li-pingho1441]

you save my life!!!!!

[@CodeEmporium]

It’s what I do best :)

[@anwarulislam6823]

How could someone hack my brain wave and convoluted this by evaluate inner voice? May I know this procedure? #Thanks

[@EngineeredFemale]

Haha ikr. I felt the same. Was looking for a good Self attention video.

[@rujutaawate5412]

Thanks, @CodeEmporium / Ajay for the great explanation! One quick question- can you please explain how the true values of Q, K, and V are actually computed? I understand that we start with random initialization but do these get updated through something like backpropagation? If you already have a video of this then would be great if you can state the name/redirect! Thanks once again for helping me speed up my AI journey! :)

[@CodeEmporium]

That's correct back prop will update these weights. For exact details, you can continue watching this playlist "Transformers From Scratch" where we will build a working transformer. This video was the first in that series. Hope you enjoy it :)

[@naziadana7885]

Thank you very much for this great video! Can you please upload a video on Self Attention code using Graph Convolutional Network (GCN)?!

[@CodeEmporium]

I’ll look into this at some point. Thanks for the tips.

[@ayush_stha]

In the demonstration, you generated the q, k & v vectors randomly, but in reality, what will the actual source of those values be?

[@CodeEmporium]

Each of the q,k,v vectors will be a function of each word (or byte pair encoding) in the sentences. I say a “function” of the sentences since to the word vectors, we add position encoding and then convert into q,k,v vectors via feed forward layers. Some of the later videos in this “Transformers from scratch”playlist show some code on exactly how it’s created. So you can check those out for more intel :)

[@SnehaSharma-nl9do]

Kannada Represent!! 🖐

[@CodeEmporium]

Haha! Yes 🙌

[@Tomcat342]

Ayo yellaru hegiddra?

[@philhamilton3946]

What is the name of the text book you are using?

[@klam77]

if u watch the vid carefully, the url shows the books are "online" free access bibles of the field.

[@sometimesdchordstrikes...7876]

@1:41 here you have said that you want the context of the words that will be coming in the future but in masking part of the video you have said that it will be cheating know the context of the words that will be coming in the future

[@goodmusic284]

This is a great tutorial. I think the links to your paid courses are broken.

[@jonfe]

i still dont understand the difference between Q K V, can someone explain?

[@ajaytaneja111]

Ajay, I don't think the point of capturing the context in terms of words 'after' has a significance in language modelling. In language modelling you are predicting only the next word. Yes, for a task like machine translation, yes. Thus I don't think Bi-directional RNNs have anything better to offer for language modelling than the regular (one-way) RNNs. . Let me know what you think

[@josephpark2093]

I watched the video around 3 times but I still don't understand. Why are these awesome videos so unknown?

[@SIADSrikanthB]

I really like how you use Kannada language examples in your explanations.

[@Slayer-dan]

Ustad 🙏

[@CodeEmporium]

too kind :)

[@ProdbyKreeper]

appreciate!

[@YT-yt-yt-3]

I felt the q, k, v parameter is not explained very well.. similar search analogy would be better to get a intuition of these parameter then explaining as what I can offer, what I actual offer

[@wishIKnewHowToLove]

thx

[@CodeEmporium]

My pleasure :)

[@kotcraftchannelukraine6118]

You forgot to show the most important thing, how to train self-attention with backpropagation? You forgot about backward pass

[@CodeEmporium]

This is the first video in a series of videos called “Transformers from scratch”. Later videos show how the entire architecture is training. Hope you enjoy the videos

[@kotcraftchannelukraine6118]

@@CodeEmporium thank you, i subscribe

[@ChethanaSomeone]

Seriously, are u from karnataka ? your accent is so different dude.

[@commonguy7]

wow

[@bkuls]

Guru aarama? Nanu kooda Kannada ne!

[@CodeEmporium]

Doin super well ma guy. Thanks for watching and commenting! :)