Rasa Algorithm Whiteboard - Transformers & Attention 2: Keys, Values, Queries 

I hereby declare this saga to be the best on Attention! Thank you so much for sharing the knowledge with such clarity!

Dear Rasa, I have watched at least 10 videos explaining this subject, and only now, after seeing your explanation, I think that I finally understand. You are a great teacher, thank you!

Finally! Finally, someone managed to explain it to me in reasonable detail and extremely clear! Thank you!

The single explanation which actually shows the motivation behind Q/K/V. Thanks.

if only the papers included the information about what the query, keys and the values actually mean! As a beginner at this field, I was having such a difficult time to wrap my head around what those actually mean. I tried convincing myself that I understood that using query and keys, we get values, but today is the day that I actually understood. Hats off sir, I want to thank you for this great explanation. The world needs teachers like you :)

The best video on attention you will found on RU-vid.

If you did not understand the explanation here, just rinse and repeat and you eventually will. This is the best explanation of keys, values and queries. Just pay attention! Thanks for putting this together!

this concept has been explained so abstractly in other videos. Props for making it intuitive, and going through the process instead of explaining the final derivation

I cannot stress how great of a teacher you are. Amazing work. Truly. I feel as though you are literally walking my stupid brain through the subject matter.

Incredible explanation! Please, keep going this kind of illustrative explanations. Congrats.

Excellent explanation. The only video among dozens I have seen that actually explains the 'why' and 'how' of using query, key and value in attention mechanism. So lucid and concise. Thank you so much.

I'm pretty impressed. I've suffered through other explanations (including from noted professors), so I've learned some things first sure. What's *excellent* about your explanations is that they are easier to follow, very well motivated (I see why we want each structure), and are bite-sized so it's not too much at once. Great job.

Truly ATTENTION is all you need to understand this piece. Great work👍

I am addicted to this video whenever I forget attentions mechanism I remember picture of 09:07

oh my god. there are SO many videos on this subject that fail to explain almost anything, probably because the presenter has no comprehension of the topic. i have been looking for this for a couple weeks now lol. just a video that states clearly "this is a vector, the output of this operation is a number" et cetera and clearly explains exactly WHAT everything is instead of vague nonsense analogies about what the pieces are. Also I have to say your handwriting/drafting skills are fantastic

Now the trilogy of Query-Keys-Values (the penny) dropped, thank you sir

I am teaching in university self attention, this video helps me a lot to find the way to explain this concept Thanks a lot for this fantastic work with Rasa and this series of videos!! A master piece

Kudos to the instructor. Very clear explanation.

Bro...when you put the analogy of query key and value that was like watching a movie and figuring out the plot twist.

Extremely clear. You are a brilliant teacher. Thank you!

This video is ALL YOU NEED to know to understand the concepts in self attention. Best explanation so far about Q, K, V terms!!!!!!

Your description developed deep understanding&knowledge of how attentions works, Thx for earliest...

JUST WOW !!! That was **SO** lucid. I understand the details of the math & the deeper intuitions all in one go. AND my brain was not over-heating with the effort.

The clarity of this video is just on whole 'nother level!

The best illustration I have ever seen.. It changed my views

You Sir, will be cited in my Master's Thesis if i end up using attention.

This is the best video. I’ve been searching for days because I don’t understand where do the key query and value come from (most other videos just talk about how the attention work but ignore how the KQVs are generated). This video solves my issue. Thumb-up!

the way you explain it is as elegant as the design of slef attention

This is the best explanation I have seen thus far. Thank you and subscribed.

I spent 2 days trying to learn attention layers in transformers. Didn't make any sense until I watched this! TYSM!!!!

Brillant lesson! For the first time, I get to understand how the analogy of key, query and value come forth. Thank you!

The best explanation about self-attention ive ever heard!! Thx a lot

3:00 thank you for this. Coming at this from a programming background and not a math background people talk about a 'dot product' and I'm here going 'I have no idea what that means'. Yes I've googled it, and I've never been sure I was doing it correctly (I wasn't) before seeing this explanation. 4:50 thank you! Other explanations were never clear if I were multiplying everything to get once number or if I were just multiplying out the array to get a new array.

Best video on attention layer there is! And the ONLY one that explains it, so that it‘s understood! Awesome work! Thank you!!

Great explanation ever heard on query key and value.

This is a fantastic video. Super intuitive storyline to unveil the concepts. Really easy to follow. If I knew someone who was trying to learn transformers I would share this with them straight away.

construction of attention from concept to implementation. excellent job

I am speechless after this high quality of explanation

These videos are excellent, and put the original paper and many webpages to shame. "These videos are all you need." (see what I did there? :-P) 'Attention' basically means: re-projecting each token from their original semantic embedding (word2vec, glove, etc.) into a new basis which is the relative similarity in meaning to other tokens in the sentence (sequence). So it should really be called "relative meaning space projection is all you need". Not as catchy, but perhaps clear. Query, key and value mean weight matrices for each time the token embeddings are used (twice in the dot product with itself to obtain the weights, and once for the input embeddings). This allows better re-embeddings (re-projections in terms of other vectors in sequence) to be learned.

Finally! attention makes all the sense in the world.

The best explanation.

Phenomenal explanation. I've watch a few other videos that left me more confused, but this finally made me understand what the purpose of the key, value, query weight matrices is. To be honest, I'm not sure whether some of the youtubers that make videos on this topic actually understand the purpose of the matrices fully. This whole series is so extremely good and helps so many beginners to better understand these models. Cannot thank you enough for making these videos. A lot of people as you can see from the comments are extremely thankful for providing such clear nicely illustrated explanations. Please keep making more videos. We all appreciate it a lot!

What a brilliant series of videos. Thank you!

You are rock! amazing, I do not know how long it takes you to get a context so clearly. but, It would take me , maybe reading many articles and finding connection maybe around 2-3 weeks!

This is incredible..... so complicated but so clear.... AMAZING WORK!!

I finally got it !! After so many videos, thank you !!!❤

This is by far the best explaination of Attention I have seen. Thank you!

Absolutely amazing. Makes SO MUCH MORE SENSE now. Thank-you :)

Seriously THE BEST videos I've ever seen on Attention and Self-Attention. Really Loved it

The best explanation I watched so far

Too good, a simple topic explained with elegance. Cheers!

Very good explanation especially with vector representation. Turns out I have heard this voice on other video tutorials too which I appreciate. Thank you!

I've done quite a lot of work on neural networks, but none on NLP. I was having trouble understanding these attention blocks but this is super clear. good stuff.

This is an absolute home run. Well done!

by far the best explanation on self attention. ty

yup, easily the best explanantion of attention. thank you for sharing!

this is a mind bogglingly awesome explanation....

finally, a great and simple explanation, thank you very much

Wonder how this video has only 4k views. Excellent explanation :(

Coolest explanation of Keys, Values and Queries!

great video. Helps explain Q,K,V in attention

Well, this got me attent! Thank you so much for the explanation, I was very confused about the V, Q, K matrices!

Explanation is brilliant!

it is incredibly wonderful explanation for this subject. thanks so much. It was a great chance to see this video. really thanks a lot

Great!!! It's the best video for explanation on Attention!

The Best Explanation on Attention PERIOD!!!

The best explanation!! You are the best .. Kudos !

OmG I can't believe I didn't discover this earlier. What a great video. Really love your way of explaining things.

Most intuitive explanation I found! Thank you :D

That was incredibly helpful, thanks!

best attention explanation on the web! THANK U!

Thanks this is tremendously helpful!

Woah...finally it all makes sense to me. Best explanation of self attention I have watched. Thanks :)

This really is the best one out there. Thank you so much

Perfect explanation. This helped a lot, thanks !

What an awesome explanation !!! Thank you Rasa very much for making this... :D

I finally understand the attention mechanism. Thank you so much

Brilliant explanation. Loved it.

Thank you, your explanation helped a lot!

beautiful explained, thanks!

Best video on attention. Thnx a lot

Excellent tutorial on Attention

I'd like this video 1000 times if I could.

oh my goodness !! you explanation is awesome.

Amazing explanation!

What an amazing lecture

Awesome video, thank you

Excellent! More please!

wow !! what a great explanation. 👍

RASA -> Real Attention Scholar Around Best!

Incredible, thank you so much

Wow! Great videos!

Amazing! Finally understood

Wow! Thank you so much I finally get it

Great video! Keep them coming

THANK YOU SO MUCH FOR THIS VIDEO!

great video, thanks!

This (and video 1) is so genius.

This an excellent explnation, thanks a lot

Just wow. You are amazing man.