This is a great video (as are the other 2) but one thing that needs to be clarified is that the embeddings themselves do not change (by attention @10:49). The gravity pull analogy is appropriate but the visuals give the impression that embedding weights change. What changes is the context vector.
Your videos in the LLM uni are incredible. Builds up true understanding after watching tons of other material that was all a bit loose on the ends. Thank you!
This video is amazing! Appreciate Luis for his skill of explaining PhD level concepts as easier that 9th grade student can understand. I found this channel is a diamond mine for beginners. Thanks Luis.
This is one of the best videos on RUclips to understand ATTENTION. Thank you for creating such outstanding content. I am waiting for upcoming videos of this series. Thank you ❤
Truly amazing video! The published papers never bother to explain things with this level of clarity and simplicity, which is a shame because if more people outside the field understood what is going on, we may have gotten something like ChatGPT about 10 years sooner! Thanks for taking the time to make this - the visual presentation with the little animations makes a HUGE difference!
This was hands down the best explanation I've seen of attention mechanisms and multi head attention --- the fact I'm able to use these words in this sentence means I understand it
Thank you for making this video series for the sake of a learner and not to show off your own knowledge!! Great anecdotes and simple examples really helped me understand the key concepts!!
Omg this video is on a whole new level . This is prolly the best intuition behind the transformers and attention. Best way to understand. I went thro' a couple of videos online and finally found the best one . Thanks a lot ! Helped me understand the paper easily
I appreciate your videos, especially how you can apply a good perspective to understand the high level concepts, before getting too deep into the maths.
These videos where you explain the transformers are excellent. I have gone through a lot of material however, it is your videos that have allowed me to understand the intuition behind these models. Thank you very much!
This is one of the clearest, simplest and the most intuitive explanations on attention mechanism.. Thanks for making such a tedious and challenging concept of attention relatively easy to understand 👏 Looking forward to the impending 2 videos of this series on attention
I always struggled with KQV in attention paper. Thanks a lot for this crystal clear explanation! Eagerly looking forward to the next videos on this topic.
This clarifies EMBEDDED matrices : - In particular the point on how a book isn't just a RANDOM array of words, Matrices are NOT a RANDOM array of numbers - Visualization for the transform and shearing really drives home the V, Q, K aspect of the attention matrix that I have been STRUGGLING to internalize Big, big thanks for putting together this explanation!
7:00 even with word embedding, words can be missing context and there’s no way to tell like the word apple. Are you taking about the company or the fruit? Attention matches each word of the input with every other word, in order to transform it or pull it towards a different location in the embedding based on the context. So when the sentence is “buy apple and orange” the word orange will cause the word apple to have an embedding or vector representation that’s closer to the fruit 8:00
Thank you for your explanation! I've always wondered why the attention mechanism in Transformers produces more effective embeddings compared to Word2Vec, and your video clarified this well. Word2Vec generates static embeddings, meaning that a word always has the same representation, regardless of the context in which it appears. In contrast, Transformers create context-dependent embeddings, where the representation of a word is influenced by the words around it. This dynamic approach is what makes Transformer embeddings so powerful.
If I understand correctly, the transformer is basically a RNN model which got intercepted by bunch of different attention layers. Attention layers redo the embeddings every time when there is a new word coming in, the new embeddings are calculated based on current context and new word, then the embeddings will be sent to the feed forward layer and behave like the classic RNN model.
I subscribe your channel immediately after watching this video, the first video I watch from your channel but also the first making me understand why embedding needs to be multiheaded. 👍🏻👍🏻👍🏻👍🏻
I've really enjoyed with that way of you described and demonstrated matrices as linear transformations. Thank you! Why, because I like Linear Algebra 😄
This is an great explanation of attention mechanism . I have enjoyed your maths for machine learning on coursera. Thank you for creating such wonderful videos
Word embeddings Vectorial representation of a word. The values in a word embedding describe various features of the words. Similar words' embeddings have a higher cosine similarity value. Attention The same word may mean different things in different contexts. How similar the word is to other words in that sentence will give you an idea as to what it really means. You start with an initial set of embeddings and take into account different words from the sentence and come up with new embeddings (trainable parameters) that better describe the word contextually. Similar/dissimilar words gravitate towards/away from each other as their updated embeddings show. Multi-head attention Take multiple possible transformations to potentially apply to the current embeddings and train a neural network to choose the best embeddings (contributions are scaled by how good the embeddings are)
First of all thank you for making these great walkthroughs of the architecture. I would really like to support your effort on this channel. let me know how I can do that. thanks
Thank you so much, I really appreciate that! Soon I'll be implementing subscriptions, so you can subscribe to the channel and contribute (also get some perks). Please stay tuned, I'll publish it here and also on social media. :)
0:55 I thought Attention mechanisms had been around for a while before this paper, e.g. Bahdanu et Al (2014) and likely even earlier than that in some form, and this paper really served as i) an illustration that attention was...well, all you needed and ii) the introduction of the Transformer model architecture?
Thanks for your great effort to make people understand it. I, however, would like ask one thing such that you have explained V is the scores. scores of what? My opninion is that the V is the key vector so that the V makes QKT matrix to vector space again. Please make it clear for better understanding. Thanks!
Thanks for the amazing videos! I am eagrly waiting for the third video. If possible please do explain the bit how the K,Q,V matrices are used on the decoder side. That would be great help.
I didn't get it on why do we add linear transformation like earlier too we had embeddings in other planes then why do shear transformation ? Please someone answer
Unless I'm mistaken, I think the linear transformations in this video incorrectly show the 2D axis as well as the object changing position, but in fact the 2D axis would stay exactly the same but with the 2D object rotating around it for example.
Paraphrase: we weigh each embedding by its score, and then add up all these weighted embeddings to obtain a really good embedding. Question to think about: why not just take the best embedding? Is it because averaging improves robustness to noise?
That is a great question! Yes, one thing is because of robustness. Also, each embedding may capture different things, one could be good for a certain topic (say, fruits) but terrible at others (say, technology). Another reason is because of continuity. Let's say that you have embedding A, which has the highest score. The moment embedding B gets a higher score, you would switch abruptly from A to B, which creates a jump discontinuity. If you take the average, instead, you would smoothly go from, say 0.51*A + 0.49*B, into 0.49^A + 0.51*B, which is very similar.
Maybe the next video will clarify how the weighting is achieved. At first I thought the V matrix provides the weighting of the different embeddings, but now I am not sure.
@@tantzer6113 yes! I thought the exact same thing, but then someone showed me they it doesn’t, those weights are recorded inside the transformer. I’m seeing that the V matrix is another embedding in which the transformation is made (and the K and Q are used to find the distances). But I’ll clarify this more in the next video.
![I.N "HALLUCINATION" | [Stray Kids : SKZ-PLAYER]](http://i.ytimg.com/vi/n5B5q1Hwt_U/mqdefault.jpg)
I have been reading the "attention is all you need" paper for like 2 years. Never understood it properly like this ever before😮. I'm so happy now🎉
This is a great video (as are the other 2) but one thing that needs to be clarified is that the embeddings themselves do not change (by attention @10:49). The gravity pull analogy is appropriate but the visuals give the impression that embedding weights change. What changes is the context vector.
Your videos in the LLM uni are incredible. Builds up true understanding after watching tons of other material that was all a bit loose on the ends. Thank you!
Best teacher on the internet, thank you for your amazing work and the time you took to put those videos together
This video is amazing!
Appreciate Luis for his skill of explaining PhD level concepts as easier that 9th grade student can understand.
I found this channel is a diamond mine for beginners.
Thanks Luis.
I love your clear, non-intimidating, and visual teaching style.
Thank you so much for your kind words and your kind contribution! It’s really appreciated!
This is one of the best videos on RUclips to understand ATTENTION. Thank you for creating such outstanding content. I am waiting for upcoming videos of this series. Thank you ❤
Truly amazing video! The published papers never bother to explain things with this level of clarity and simplicity, which is a shame because if more people outside the field understood what is going on, we may have gotten something like ChatGPT about 10 years sooner! Thanks for taking the time to make this - the visual presentation with the little animations makes a HUGE difference!
best description ever! easy to understand. I've been suffered to understanding attention. Finally I can tell I know it!
The world needs people like Serrano more, who explain the shit out of ambiguities and lead us back to the age of wisdom.
Just THANK YOU. This is by far the best video on the attention mechanism for people that learn visually
This was hands down the best explanation I've seen of attention mechanisms and multi head attention --- the fact I'm able to use these words in this sentence means I understand it
THE best explanation of this concept. That was genuinely amazing.
This channel is uderrated, your explainations is the best among other channels
That was awesome, Thank you.
You saved me a lot of time reading and watching none-sense videos and texts
.
Thank you for making this video series for the sake of a learner and not to show off your own knowledge!! Great anecdotes and simple examples really helped me understand the key concepts!!
Omg this video is on a whole new level . This is prolly the best intuition behind the transformers and attention. Best way to understand. I went thro' a couple of videos online and finally found the best one . Thanks a lot ! Helped me understand the paper easily
absolutely loved the last part with explaining linear transformations of query key and values. thank you so much!
I appreciate your videos, especially how you can apply a good perspective to understand the high level concepts, before getting too deep into the maths.
So glad to see you're still active Luis ! You and Statquest's Josh Stamer really are the backbone of more ml professionals than you can imagine
These videos where you explain the transformers are excellent. I have gone through a lot of material however, it is your videos that have allowed me to understand the intuition behind these models. Thank you very much!
One of the best intuitions for understanding multi-head attention. Thanks a lot!❣
This is one of the clearest, simplest and the most intuitive explanations on attention mechanism.. Thanks for making such a tedious and challenging concept of attention relatively easy to understand 👏 Looking forward to the impending 2 videos of this series on attention
The way you break down these concepts is insane. Thank you
I really enjoyed how you give a clear explanation of the operations and the representations used in attention
This is such a good, clear and concise video. Great job!
I always struggled with KQV in attention paper. Thanks a lot for this crystal clear explanation!
Eagerly looking forward to the next videos on this topic.
What a beautiful way of explaining "Attention Mechanism". Great job Serano
Fantastic !!! The explanation itself is a piece of art.
The step by step approach, the abstractions, ... Kudos!!
Please more of these
Great explanation. After watching a handful of videos this one really makes it real easy to understand.
amazing explanation Luis. Can't thank you enough for your amazing work. You have a special gift to explain things. Thanks.
this video is really teaching you the intuition. much better than the others I went through that just throw formula to you. thanks for the great job!
Wow, clearest example yet. Thanks for making this!
This clarifies EMBEDDED matrices :
- In particular the point on how a book isn't just a RANDOM array of words, Matrices are NOT a RANDOM array of numbers
- Visualization for the transform and shearing really drives home the V, Q, K aspect of the attention matrix that I have been STRUGGLING to internalize
Big, big thanks for putting together this explanation!
7:00 even with word embedding, words can be missing context and there’s no way to tell like the word apple. Are you taking about the company or the fruit?
Attention matches each word of the input with every other word, in order to transform it or pull it towards a different location in the embedding based on the context. So when the sentence is “buy apple and orange” the word orange will cause the word apple to have an embedding or vector representation that’s closer to the fruit
8:00
Thank you for your explanation! I've always wondered why the attention mechanism in Transformers produces more effective embeddings compared to Word2Vec, and your video clarified this well. Word2Vec generates static embeddings, meaning that a word always has the same representation, regardless of the context in which it appears. In contrast, Transformers create context-dependent embeddings, where the representation of a word is influenced by the words around it. This dynamic approach is what makes Transformer embeddings so powerful.
Thanks Luis, been following your contents for a while. This video about attention mechanism is very intuitive and easy to follow
Hey Louis, you are AMAZING! Your explanations are incredible.
Wooow thanks so much. You are a treasure to the world. Amazing teacher of our time.
The most easy to understand video for the subject I've seen.
Kudos to your efforts in clear explanation!
best explanation of embeddings I've seen, thank you!
Excellent video. Best explanation on the internet !
If I understand correctly, the transformer is basically a RNN model which got intercepted by bunch of different attention layers. Attention layers redo the embeddings every time when there is a new word coming in, the new embeddings are calculated based on current context and new word, then the embeddings will be sent to the feed forward layer and behave like the classic RNN model.
Can anyone confirm this?
Amazing video... Thanks sir for this pictorial representation and explaining this complex topic with such an easy way.
El mejor video que he visto sobre la materia. Muchísimas gracias por este gran trabajo.
I subscribe your channel immediately after watching this video, the first video I watch from your channel but also the first making me understand why embedding needs to be multiheaded. 👍🏻👍🏻👍🏻👍🏻
Nicely done! This gives a great explanation of the function and value of the projection matrices.
This is amazingly clear! Thank for your your work!
Deep respect, Luis Serrano! Thank you so much!
It's so great, I finally understand these qkvs, it bothers me so long. Thank you so much !!!
Thanks, the explaination is so intuitive. Finally understood the idea of attention.
I did not even realize this video is 21 minutes long. Great explanation.
It was the most useful video explaining attention mechanism. Thank you
Well the gravity example is how I understood this after a long time. you are true legend.
amazing, love your channel. It's certainly underrated.
You're my fav teacher. Thank you Luis 😊
Great explanation with the linear transformation matrices. Thanks!
What a great explanation on this topic! Great job!
This is the most amazing video on "Attention is all you need"
Outstanding, thank you for this pearl of knowledge!
This video helps to explain the concept in a simple way.
What a great video man!!! Thanks for making such videos.
I've really enjoyed with that way of you described and demonstrated matrices as linear transformations. Thank you! Why, because I like Linear Algebra 😄
Amazing! Loved it! Thanks a lot Serrano!
Explained very well. Thank you so much.
Luis Serrano you have a gift for explain! Thank you for sharing!
Great video and very intuitive explenation of attention mechanism
I watched a lot about attentions. You are the best. Thank you thank you. I am also learning how to explain of a subject from you 😊
Great explanation. Thank you very much for sharing this.
Thanks for sharing. Your videos are helping me in my job. Thank you.
Very impressed with this channel and presenter
This is an great explanation of attention mechanism . I have enjoyed your maths for machine learning on coursera. Thank you for creating such wonderful videos
Word embeddings
Vectorial representation of a word. The values in a word embedding describe various features of the words. Similar words' embeddings have a higher cosine similarity value.
Attention
The same word may mean different things in different contexts. How similar the word is to other words in that sentence will give you an idea as to what it really means.
You start with an initial set of embeddings and take into account different words from the sentence and come up with new embeddings (trainable parameters) that better describe the word contextually. Similar/dissimilar words gravitate towards/away from each other as their updated embeddings show.
Multi-head attention
Take multiple possible transformations to potentially apply to the current embeddings and train a neural network to choose the best embeddings (contributions are scaled by how good the embeddings are)
Amazing explanation Luis! As always...
Merci Louis! :)
First of all thank you for making these great walkthroughs of the architecture. I would really like to support your effort on this channel. let me know how I can do that. thanks
Thank you so much, I really appreciate that! Soon I'll be implementing subscriptions, so you can subscribe to the channel and contribute (also get some perks). Please stay tuned, I'll publish it here and also on social media. :)
This is amazing explanation! Thank you so much 🎉
0:55 I thought Attention mechanisms had been around for a while before this paper, e.g. Bahdanu et Al (2014) and likely even earlier than that in some form, and this paper really served as i) an illustration that attention was...well, all you needed and ii) the introduction of the Transformer model architecture?
Thank you so much for the attention to the topic!
Thanks! Lol, I see what you did there! :D
Incredible explanation. Thank you so much!!!
Wow wow wow! I enjoyed the video. Great teaching sir❤❤
You are great at teaching Mr. Luis
Superb explanation❤ please make more videos like this
Excellent explanation. Thank you very much.
Wooow. Such a good explanation for embedding. Thanks 🎉
Thanks!
¡Gracias!
Muchisimas gracias por tu colaboración!!! Que amable!
Outstanding video. Amazing to gain intuition.
Thanks for your great effort to make people understand it. I, however, would like ask one thing such that you have explained V is the scores. scores of what? My opninion is that the V is the key vector so that the V makes QKT matrix to vector space again. Please make it clear for better understanding. Thanks!
Thanks for the amazing videos! I am eagrly waiting for the third video. If possible please do explain the bit how the K,Q,V matrices are used on the decoder side. That would be great help.
I didn't get it on why do we add linear transformation like earlier too we had embeddings in other planes then why do shear transformation ? Please someone answer
Thanks. I saw also your "Math behind" video, but still missing the third in the series.
Thanks! The third video is out now! ruclips.net/video/qaWMOYf4ri8/видео.html
Thank you for this amazing explanation
This was great - really well done!
Thank you so much for making these videos!
Unless I'm mistaken, I think the linear transformations in this video incorrectly show the 2D axis as well as the object changing position, but in fact the 2D axis would stay exactly the same but with the 2D object rotating around it for example.
Amazing video, thank you very much for sharing!
Paraphrase: we weigh each embedding by its score, and then add up all these weighted embeddings to obtain a really good embedding. Question to think about: why not just take the best embedding? Is it because averaging improves robustness to noise?
That is a great question! Yes, one thing is because of robustness. Also, each embedding may capture different things, one could be good for a certain topic (say, fruits) but terrible at others (say, technology).
Another reason is because of continuity. Let's say that you have embedding A, which has the highest score. The moment embedding B gets a higher score, you would switch abruptly from A to B, which creates a jump discontinuity. If you take the average, instead, you would smoothly go from, say 0.51*A + 0.49*B, into 0.49^A + 0.51*B, which is very similar.
Thanks for the answer, and for the wonderful video.
Maybe the next video will clarify how the weighting is achieved. At first I thought the V matrix provides the weighting of the different embeddings, but now I am not sure.
@@tantzer6113 yes! I thought the exact same thing, but then someone showed me they it doesn’t, those weights are recorded inside the transformer. I’m seeing that the V matrix is another embedding in which the transformation is made (and the K and Q are used to find the distances). But I’ll clarify this more in the next video.
Amazing explanation 🎉
That's an awesome explanation! Thanks!