incredibly well explained, thanks a lot!

This was an awesome explanation! One small question (maybe correction?) - at around 7:20 shouldn't the Gini index of the diverse set be 1 - (0 + 0 + ... +0) since the probability of getting the same element twice is 0 - there are 10 unique elements i.e. no duplicates, so it's impossible to pick two of the same item.

Thank you,professor,you have saved my life.

Your last video was good. But in this video, you didnt explain a lot about the keys and queries vectors (your explanation was very generic). It would have helped if you had deep dived a little more with examples for explaining this. Overall, I really like your videos, but there is scope of improvement. Thanks

Great explanation sir...

Luis, I really liked the explanation of pseudo code, 😊 Thankyou for connecting on LinkedIn ❤

This is probably the most friendliest video and still covering all important concepts of RL, thank you

Uau! Amazing! Thanks for the simplest explanation I've ever seen 🙂

This is just Gold!!!!!

You are the best expainer ever. You are amazing.

Stop LGBT & AI. Vote MAGA! Vote Trump!!! AI is heresy.

@SerranoAcademy , Thank you this is awesome video. At time slot 25 mins - you are explaining that during the math Q(Orange) * WQ * WK * K(Phone) - WQ and WK helps to transform the embedding. This seems to incorrect - because, even before self attention - q is multiplied with WQ to get Q and same for K. So, the actual math is q *WQ * k * WK - since matrix multiplication is not commutative - you can't do that. So it looks like we are finding the similarity between Q and K where as Q and K belong to different embedding space. Not sure how it actually works as per you explanation. It would he helpful if you could answer it. Thanks.

tf just i saw, you are God

29:00 thanks for the great video. But we can't just pick the greater number each day. We should have recorded the hidden state that led to the bigger probability and use that info to build the path

what is the true value of V,K,Q matrix ?

A professor here - preparing for my couse and tryng to find an easier way to talk about these ideas. I learned a lot! Thank you!

Wonderful! Thanks so much!

getting to see this after a heavy day at work is refreshing.. Thank you so much for sharing

Dude, thanks a ton for explaining this so simply

Thank you so much! Another amazing tutorial!!!

That is the best explanation of Gini impurity I’ve ever seen! Even 8-year-old children can get it. Amazing! Congrats Luis Serrano/Serrano Academy!!

Awesome examples & explanation. TY

I love your clear, non-intimidating, and visual teaching style.

So good. Thank you.

wow, that was wonderful explanation. thatnks!

Reading the book is really hard. It's hard to control the studying environment, and it's hard to sustain enough focus with the necessary momentum to learn a concept. Theres so many interruptions that can happen that can interfere with the process, but with this concise and powerful video it helped save a lot of time in learning. Thanks.❤

Thanks. I really had a FOMO. Best of luck❤

What an intuitive explanation! Kudos to you!

Your explanation is almost like an elementary school teacher. regression is addng and subtracting to slope and y-intercept. couldn't get easier than this. great!

Great finish! I have trained a few models. I understood conceptially.

This is the best ever video you will find on HMM. Complicated concepts handled soooo wellll🥰

Absolutely brilliant red blue glove experiment and how observation changes values. 🎉

Exciting. A conceptual journey. 🎉

Muy BALL-issimo 😄 Loved the puns!!!!!😋😋😋

Really enjoyable, really understandable intro to RNN. Loved it - many thanks. But there is a tiny error at 18:07 that might cause a little confusion for us newbies when doing the 'Add' layer calculations for the graphical version of the RNN: The output of the 'Add' layer should read 100121, not 010121

Thank you for this fantastic video series on Transformers! The first two videos were particularly enlightening. I'm fascinated by how the query, key, and value vectors evolve before each attention module. It would be wonderful to gain a deeper understanding of the encoder-decoder architecture, particularly why the first attention belongs to the encoder while the subsequent ones are part of the decoder. Also, I'm intrigued by the visualization of linear transformations at each step during training, especially when outputs are recycled back into the decoder. Eagerly awaiting more insights!

Your explanation is so great. Keep going on my friend. I am waiting for your next video.

Just a superb explanation!

Thank you for your great video, but how did the correlation between D and AC, E and B, come about? Why does this specific correlation form?

La mejor explicación que he visto sobre los Transformers. Gracias!

Thanks! This is one of the best explanations of Q, K & V I've heard!

really helpful！

Thanks for the Great video! Your content on Udacity is outstanding too!

india sok asik

I'm so glad to know there are others who do this!!! I've been doing this pattern since I was 10 years old, and still do it obsessively in middle age. I see it as a pressure release for my brain--if I am stressed, anxious, or just don't have enough to occupy my brain, it activates this pattern in my shoulders, toes, any symmetrical body parts.

13:32 "feel free to pause the video" reminds me of Chess KZbinr agadmator 🤣

Here in 2024 and been trying to wrap my brain around this stuff for a couple years. Your vids have absolutely made it all click. Well done and many thanks!

Wow excellent video, without any background on GMM I was able to understand the concept and logic behind it. Gracias!!

kzbin.info/aero/PLDP4z80c2BiL40zhQyiITTSVFve_2e-tJ&si=ktBvnZlHjD2kLkNq

amazing video. that's what i looking for. I need to know mathematical background to understand what is happening behind. thank you sir!