Attention for Neural Networks, Clearly Explained!!!

Attention is one of the most important concepts behind Transformers and Large Language Models, like ChatGPT. However, it's not that complicated. In this StatQuest, we add Attention to a basic Sequence-to-Sequence (Seq2Seq or Encoder-Decoder) model and walk through how it works and is calculated, one step at a time. BAM!!!
NOTE: This StatQuest is based on two manuscripts. 1) The manuscript that originally introduced Attention to Encoder-Decoder Models: Neural Machine Translation by Jointly Learning to Align and Translate: arxiv.org/abs/1409.0473 and 2) The manuscript that first used the Dot-Product similarity for Attention in a similar context: Effective Approaches to Attention-based Neural Machine Translation arxiv.org/abs/1508.04025
NOTE: This StatQuest assumes that you are already familiar with basic Encoder-Decoder neural networks. If not, check out the 'Quest: • Sequence-to-Sequence (...
If you'd like to support StatQuest, please consider...
Patreon: / statquest
...or...
KZbin Membership: / @statquest
...buying my book, a study guide, a t-shirt or hoodie, or a song from the StatQuest store...
statquest.org/statquest-store/
...or just donating to StatQuest!
www.paypal.me/statquest
Lastly, if you want to keep up with me as I research and create new StatQuests, follow me on twitter:
/ joshuastarmer
0:00 Awesome song and introduction
3:14 The Main Idea of Attention
5:34 A worked out example of Attention
10:18 The Dot Product Similarity
11:52 Using similarity scores to calculate Attention values
13:27 Using Attention values to predict an output word
14:22 Summary of Attention
#StatQuest #neuralnetwork #attention

[@statquest]

To learn more about Lightning: lightning.ai/ Support StatQuest by buying my book The StatQuest Illustrated Guide to Machine Learning or a Study Guide or Merch!!! statquest.org/statquest-store/

[@koofumkim4571]

“Statquest is all you need” - I really needed this video for my NLP course but glad it’s out now. I got an A+ for the course, your precious videos helped a lot!

[@statquest]

BAM! :)

[@atharva1509]

Somehow Josh always figures out what video are we going to need!

[@yashgb]

Exactly, I was gonna say the same 😃

[@statquest]

BAM! :)

[@yesmanic]

Same here 😂

[@MelUgaddan]

The level of explainability from this video is top-notch. I always watch your video first to grasp the concept then do the implementation on my own. Thank you so much for this work !

[@statquest]

Glad it was helpful!

[@Travel-Invest-Repeat]

Great work, Josh! Listening to my deep learning lectures and reading papers become way easier after watching your videoes, because you explain the big picture and the context so well!! Eagerly waiting for the transformers video!

[@statquest]

Coming soon! :)

[@clockent]

This is awesome mate, can't wait for the next installment! Your tutorials are indispensable!

[@statquest]

Thank you!

[@rajapandey2039]

@@statquest BAM!

[@rutvikjere6392]

I was literally trying to understand attention a couple of days ago and Mr.BAM posts a video about it. Thanks 😊

[@NoahElRhandour]

same :D abesolutely insane...

[@statquest]

BAM! :)

[@Murattheoz]

I feel like I am watching a cartoon as a kid. :)

[@statquest]

bam!

[@dylancam812]

Dang this came out just 2 days after my neural networks final. I’m still so happy to see this video in feed. You do such great work Josh! Please keep it up for all the computer scientists and statisticians that love your videos and eagerly await each new post

[@statquest]

Thank you very much! :)

[@Neiltxu]

@@statquest it came out 3 days before my Deep Learning and NNs final. BAM!!!

[@statquest]

@@Neiltxu Awesome! I hope it helped!

[@Neiltxu]

@@statquest for sure! Your videos always help! btw, do you ship to spain? I like the hoodies of your shop

[@statquest]

@@Neiltxu I believe the hoodies ship to Spain. Thank you for supporting StatQuest! :)

[@aayush1204]

1 million subscribers INCOMING!!! Also huge thanks to Josh for providing such insightful videos. These videos really make everything easy to understand, I was trying to understand Attention and BAM!! found this gem.

[@statquest]

Thank you very much!!! BAM! :)

[@SharingFists]

This channel is pure gold. I'm a machine learning and deep learning student.

[@statquest]

Thanks!

[@aquater1120]

I was just reading the original attention paper and then BAM! You uploaded the video. Thank you for creating the best content on AI on KZbin!

[@statquest]

Thank you very much! :)

[@ArpitAnand-yd7tr]

The best explanation of Attention that I have come across so far ... Thanks a bunch❤

[@statquest]

Thank you very much! :)

[@sinamon6296]

Hi mr josh, just wanna say that there is literally no one that makes it so easy for me to understand such complicated concepts. Thank you ! once I get a job I will make sure to give you guru dakshina! (meaning, an offering from students to their teachers)

[@statquest]

Thank you very much! I'm glad my videos are helpful! :)

[@linhdinh136]

Thanks for the wholesome contents! Looking for Statquest video on the Transformer.

[@statquest]

Wow!!! Thank you so much for supporting StatQuest!!! I'm hoping the StatQuest on Transformers will be out by the end of the month.

[@linhdinh136]

❤

[@d_b_]

Thanks for this. The way you step through the logic is always very helpful

[@statquest]

Thanks!

[@brunocotrim2415]

Hello Statquest, I would like to say Thank You for the amazing job, this content helped me understand a lot how Attention works, specially because visual things help me understand better, and the way you join the visual explanation with the verbal one while keeping it interesting is on another level, Amazing work

[@statquest]

Thank you!

[@KevinKansas1]

The way you explain complex subjects in a easy-to-understand format is amazing! Do you have an idea when will you release a video about transformers? Thank you Josh!

[@statquest]

I'm shooting for the end of the month.

[@JeremyHalfon]

Hi Josh@@statquest , any update on the following? Would definitely need it for my final tomorrow :))

[@statquest]

@@JeremyHalfon I'm finishing my first draft today. Hope to edit it this weekend and record next week.

[@ncjanardhan]

The BEST explanation of Attention models!! Kudos & Thanks 😊

[@statquest]

Thank you very much!

[@saschahomeier3973]

You have a talent for explaining these things in a straightforward way. Love your videos. You have no video about Transformers yet, right?

[@statquest]

The transformers video is currently available to channel members and patreon supporters.

[@weiyingwang2533]

You are amazing! The best explanation I've ever found on KZbin.

[@statquest]

Wow, thanks!

[@familywu3869]

Thank you for the excellent teaching, Josh. Looking forward to the Transformer tutorial. :)

[@statquest]

Coming soon!

[@benmelis4117]

I just wanna let you know that this series is absolutely amazing. So far, as you can see, I've made it to the 89th video, guess that's something. Now it's getting serious tho. Again, love what you're doing here man!!! Thanks!!

[@statquest]

Thank you so much!

[@benmelis4117]

@@statquest Personally, since I'm a medical student, I really can't explain how valuable it is to me that you used so many medical examples in the video's. The moment you said in one of the first video's that you are a geneticist I was sold to this series, it's one of my favorite subjects at uni, crazy interesting!

[@statquest]

@@benmelis4117 BAM! :)

[@lunamita]

Can’t thank enough for this guy helped me get my master degree in AI back in 2022, now I’m working as a data scientist and still kept going back to your videos.

[@statquest]

BAM!

[@won20529jun]

I was literally just thinking an Id love an explanation of attention by SQ..!!! Thanks for all your work

[@statquest]

bam!

[@rafaeljuniorize]

this was the most beautiful explanation that i ever had in my entire life, thank you!

[@statquest]

Wow, thank you!

[@mehmeterenbulut6076]

I was stunned when you start the video with a catch jingle man, cheers :D

[@statquest]

:)

[@MartinGonzalez-wn4nr]

Hi Josh, I just bought your books, Its amazing the way that you explain complex things, read the papers after wach your videos is easier. NOTE: waiting for the video of transformes

[@statquest]

Glad you like them! I hope the video on Transformers is out soon.

[@tupaiadhikari]

Thanks Professor Josh for such a great tutorial ! It was very informative !

[@statquest]

My pleasure!

[@The-Martian73]

Great, that's really what I was looking for, thanks mr Starmer for the explanation ❤

[@statquest]

bam! :)

[@usser-505]

The end is a classic cliffhanger for the series. You talk about how we don't need the LSTMs and I wait for an entire summer for transformers. Good job! :)

[@statquest]

Ha! The good news is that you don't have to wait! You can binge! Here's the link to the transformers video: kzbin.info/www/bejne/sKm0qoeBbdaor7s

[@usser-505]

@@statquestYeah! I already watched when you released it. I commented on how this deep learning playlist is becoming a series! :)

[@statquest]

@@usser-505 bam!

[@okay730]

I'm excited for the video about transformers. Thank you Josh, your videos are extremely helpful

[@statquest]

Coming soon!

[@capyk5455]

You're amazing Josh, thank you so much for all this content

[@statquest]

Glad you enjoy it!

[@ArpitAnand-yd7tr]

Really looking forward to your explanation of Transformers!!!

[@statquest]

Thanks!

[@abdullahhashmi654]

Been wanting this video for so long, gonna watch it soon!

[@statquest]

bam!

[@jacobverrey4075]

Josh - I've read the original papers and countless online explanations, and this stuff never makes sense to me. You are the one and only reason as to why I understand machine learning. I wouldn't be able to make any progress on my PhD if it wasn't for your videos.

[@statquest]

Thanks! I'm glad my videos are helpful! :)

[@chessplayer0106]

Ah excellent this is exactly what I was looking for!

[@statquest]

Thank you!

[@birdropping]

@@statquest Can't wait for the next episode on Transformers!

[@hasansayeed3309]

Amazing video Josh! Waiting for the transformer video. Hopefully it'll come out soon. Thanks for everything!

[@statquest]

Thanks! I'm working on it! :)

[@rathinarajajeyaraj1502]

Much awaited one .... Awesome as always ..

[@statquest]

Thank you!

[@abdullahbinkhaledshovo4969]

I have been waiting for this for a long time

[@statquest]

Transformers comes out on monday...

[@rrrprogram8667]

Excellent josh.... So finally MEGA Bammm is approaching..... Hope u r doing good...

[@statquest]

Yes! Thank you! I hope you are doing well too! :)

[@envynoir]

Godsent! Just what I needed! Thanks Josh.

[@statquest]

bam!

[@abrahammahanaim3859]

Hey Josh your explanation is easy to understand. Thanks

[@statquest]

Glad it was helpful!

[@yizhou6877]

I am always amazed by your tutorials! Thanks. And when we can expect the transformer tutorial to be uploaded?

[@statquest]

Tonight!

[@yoshidasan4780]

first of all thanks a lot Josh! you made it way too understandable for us and i would be forever grateful to you for this !! Have a nice time! and can you please upload videos on Bidirectional LSTM and BERT?

[@statquest]

I'll keep those topics in mind.

[@AntiPolarity]

can't wait for the video about Transformers!

[@statquest]

Me too!

[@souravdey1227]

Had been waiting for this for months.

[@statquest]

The wait is over! :)

[@user-fj2qq7cp2n]

Thank you very much for your explanation! You are always super clear. Will the transformer video be out soon? I have a natural language processing exam in a week and I just NEED your explanation to go through them 😂

[@statquest]

Unfortunately I still need a few weeks to work on the transformers video... :(

[@gordongoodwin6279]

fun fact - if your vectors are scaled/mean-centered, cosine similarity is geometrically equivalent to the pearson correlation, and the dotproduct is the same as the covariance (un-scaled correlation).

[@statquest]

nice.

[@rajatjain7894]

Was eagerly waiting for this video

[@statquest]

Bam! :)

[@owlrion]

Hey! Great video, this is really helping me with neural networks at the university, do we have a date for when the transformer video comes out?

[@statquest]

Soon....

[@sabaaslam781]

Hi Josh! No doubt, you teach in the best way. I have a request, I have been enrolled in PhD and going to start my work on Graphs, Can you please make a video about Graph Neural Networks and its variants, Thanks.

[@statquest]

I'll keep that in mind.

[@sreerajnr689]

Your explanation is AMAZING AS ALWAYS!! I have 1 doubt. Do we do the attention calculation only on the final layer? For example, if there are 2 layers in encoder and 2 layers in decoder, we use only the outputs from 2nd layer of encoder and 2nd layer of decoder for attention estimation, right?

[@statquest]

I believe that is correct, but, to be honest, I don't think there is a hard rule.

[@imkgb27]

Many thanks for your great video! I have a question. You said that we calculate the similarity score between 'go' and EOS (11:30). But I think the vector (0.01,-0.10) is the context vector for "let's go" instead of "go" since the input includes the output for 'Let's' as well as the embedding vector for 'go'. It seems that the similarity score between 'go' and EOS is actually the similarity score between "let's go" and EOS. Please make it clear!

[@statquest]

You can talk about it either way. Yes, it is the context vector for "Let's go", but it's also the encoding, given that we have already encoded "Let's", of the word "go".

[@rikki146]

When I see new vid from Josh, I know today is a good day! BAM!

[@statquest]

BAM! :)

[@rishabhsoni]

Superb Videos. One question, is the fully connected layer just simply the softmax layer, there is no hidden layer with weights (meaning no weights are learned)?

[@statquest]

No, there are weights along the connections between the input and output of the fully connected layer, and those outputs are then pumped into the softmax. I apologize for not illustrating the weights in this video. However, I included them in my video on transformers, and it's the same here. Here's the link to the transformers video: kzbin.info/www/bejne/sKm0qoeBbdaor7s

[@markus_park]

Thanks! This was a great video!

[@statquest]

Thank you very much! :)

[@manuelcortes1835]

I have a question that could benefit from clarification: In the final FC layer for word predictions, it is claimed that the Attention Values and 'encodings' are used as input (13:38). By 'encodings', do we mean the short term memories from the top LSTM layer in the decoder?

[@statquest]

Yes. We use both the attention values and the LSTM outputs (short-term memories or hidden states) as inputs to the fully connected layer.

[@naomilago]

The music sang before the video are contagious ❤

[@statquest]

:)

[@luvxxb]

thank you so much for making these great materials

[@statquest]

Thanks!

[@akashat1836]

Hey Josh! Firstly, Thank you so much for this amazing content!! I can always count on your videos for a better explanation! I have one quick clarification to make. Before the fully dense layer. The first two numbers we get are from the [scaled(input1-cell1) + scaled(input2-cell1) ] and [scaled(input1-cell2) + scaled(input2-cell2) ] right? And the other two numbers are from the outputs of the decoder, right?

[@statquest]

Yes.

[@akashat1836]

@@statquest Thank you for the clarification!

[@carloschau9310]

thank you sir for your brilliant work!

[@statquest]

Thank you!

[@theelysium1597]

Since you asked for video suggestions in another video: A video about the EM and Mean Shift algorithm would be great!

[@statquest]

I'll keep that in mind.

[@Rykurex]

Do you have any courses with start-to-finish projects for people who are only just getting interested in machine learning? Your explanations on the mathematical concepts has been great and I'd be more than happy to pay for a course that implements some of these concepts into real world examples

[@statquest]

I don't have a course, but hope to have one one day. In the meantime, here's a list of all of my videos somewhat organized: statquest.org/video-index/ and I do have a book called The StatQuest Illustrated Guide to Machine Learning: statquest.org/statquest-store/

[@madjohnshaft]

I am currently taking the AI cert program from MIT - I thank you for your channel

[@statquest]

Thanks and good luck!

[@arvinprince918]

hey there josh @statquest, your videos are really awsome and super helpful, thus i was wondering when will your video for transformer model come out

[@statquest]

All channel members and patreon supports have access to it right now. It will be available to everyone else in a few weeks.

[@SaumitraAgrawalB22AI054]

in the decoder part, the second time when we are passing vamos as input, do we have to calculate the similarity score again? or we should be using the old one only?

[@statquest]

In the decoder we start by calculating the similarity between the token and the input tokens. Then we calculate the similarity between "vamos" and the input tokens. So those are two different similarity calculations.

[@saumitragrawal2279]

Thankyou Got it

[@Xayuap]

weeeeee, video for tonite, tanks a lot

[@statquest]

:)

[@handsomemehdi3445]

Hello, Thank you for the video, but I am so confused that some terms introduced in original 'Attention is All You Need' paper were not mentioned in video, for example, keys, values, and queries. Furthermore, in the paper, authors don't talk about cosine similarity and LSTM application. Can you please clarify this case a little bit much better?

[@statquest]

The "Attention is all you need" manuscript did not introduce the concept of attention. That does done years earlier, and that is what this video describes. If you'd like to understand the "Attention is all you need" concept of transformers, check out my video on transformers here: kzbin.info/www/bejne/sKm0qoeBbdaor7s

[@lequanghai2k4]

I am stilling learning this so hope next video come out soon

[@statquest]

I'm working on it as fast as I can.

[@jarsal_firahel]

Before, I was dumb, "guitar" But now, people say I'm smart "guitar" What is changed ? "guitar" Now I watch..... StatQueeeeeest ! "guitar guitar"

[@statquest]

bam!

[@miladafrasiabi5499]

Thank you for the awesome video. I have a question. What does the similarity score entails in reality? I assume that the Ws and Bs are being optimized by backpropagation in order to give larger positive values to synonyms, close to 0 values to unrelated words and large negative values to antonyms. Is this a right assumption?

[@statquest]

I believe that is correct. However, if there is one thing I've learned about neural networks, it's that the weights and biases are optimized only to fit the data and the actual values may or may not make any sense beyond that specific criteria.

[@thanhtrungnguyen8387]

can't wait for the next StatQuest

[@statquest]

:)

[@thanhtrungnguyen8387]

@@statquest I'm currently trying to fine-tune Roberta so I'm really excited about the following video, hope the following videos will also talk about BERT and fine-tune BERT

[@statquest]

@@thanhtrungnguyen8387 I'll keep that in mind.

[@alexfeng75]

Fantastic video, indeed! Is the attention described in the video the same as in the attention paper? I didn't see the mention of QKV in the video and would like to know whether it was omitted to simplify or by mistake.

[@statquest]

Are you asking about the QKV notation that appears in the "Attention is all you need" paper? That manuscript arxiv.org/abs/1706.03762 , which came out in 2017, didn't introduce the concept of attention for neural networks. Instead it introduces a more advanced topic - Transformers. The original "how to add attention to neural networks" manuscript arxiv.org/pdf/1409.0473.pdf came out in 2015 and did not use the QKV notation that appeared later in the transformer manuscript. Anyway, my video follows the original, 2015, manuscript. However, I'm working on a video that covers the 2017 manuscript right now. And I've got a long section talking all about the QKV stuff in it. That said, in this video, you can think of the output from each LSTM in the decoder as a "Query", and the outputs from each LSTM in the Encoder as the "Keys" and "Values". The "Keys" are used, in conjunction with each "Query" to calculate the Similarity Scores and the "Values" are then scaled by those scores to create the attention values.

[@alexfeng75]

@@statquest Thanks for the reply, Josh. Yes, I was referring to the 2017 paper. I look forward to your video covering it.

[@Ghost-ip3bx]

Hi StatQuest, I've been a long time fan, your videos have helped me TREMENDOUSLY. For this video I felt however if we could get a larger picture of how attention works first ( how different words can have different weights ( attending to them differently )) and then going through a run with actual values, it'd be great! :) I also felt that the arrows and diagrams got a bit confusing in this one. Again, this is only constructive criticism and maybe it works for others and just not for me ( this video I mean ). Nonetheless, thank you so much for all the time and effort you put into making your videos. You're helping millions of people out there clear their degrees and achieve life goals

[@statquest]

Thanks for the feedback! I'm always trying to improve how I make videos. Anyway, I work through the concepts more in my videos on transformers: kzbin.info/www/bejne/sKm0qoeBbdaor7s and if the diagrams are hard to follow, I also show how it works using matrix math: kzbin.info/www/bejne/gaHLnoKAo7F0mqs

[@andresg3110]

You are on Fire! Thank you so much

[@statquest]

Thank you! :)

[@orlandopalmeira623]

Hello, I have a doubt. The initialization of the cell state and hidden state of the decoder is a context vector that is the representation (generated by encoder) of the entire sentence (input)? And what about each hidden state (from encoder) used in decoder? Are they stored somehow? Thanks!!!

[@statquest]

1) Yes, the context vector is a representation of the entire input. 2) The hidden states in the encoder are stored for attention.

[@orlandopalmeira623]

@@statquest Thanks!!

[@patrikszepesi2903]

Hi, great video. At 13:49 can you please explain how you get -.3 and 0.3 for the input to the fully connected? THank you

[@statquest]

The outputs from the softmax function are multiplied with the short-term memories coming out of the encoders LSTM units. We then add those products together to get -0.3 and 0.3.

[@juliank7408]

Phew! Lots of things in this model, my brain feels a bit overloaded, haha But thanks! Might have to rewatch this

[@statquest]

You can do it!

[@tupaiadhikari]

At 13:38 are we Concatenating the output of the attention values and the output of the decoder LSTM for the translated word (EOS in this case) and then using a weights of dimensions (4*4) to convert into a dimension 4 pre Softmax output?

[@statquest]

yep

[@statquest]

If you want to see a more detailed view of what is going on at that stage, check out my video on Transformers: kzbin.info/www/bejne/sKm0qoeBbdaor7s In that video, I go over every single mathematical operation, rather than gloss over them like I do here.

[@tupaiadhikari]

@@statquest Thank You Professor Josh for the clarifications !

[@sciboy123]

I had a little confusion about the final fully connected layer. It takes in separate attention values for each input word. But doesn't this mean that the dimension of the input depends on how many input words there are (thus it would be difficult to generalize for arbitrarily long sentences)? Did I misunderstand something?

[@statquest]

I can see why this might be confusing because we have 2 input words and two inputs for attention going into the final fully connected layer. However, the number of inputs for attention going into the final fully connected layer is not determined by the number of input words, instead it is determined by the number of LSTM cells we have per layer (or, alternatively, the number of output values from the LSTMs per layer). In this case, we have 2 LSTM cells in a single layer. And thus, regardless of the number of input words, there will only be 2 attention values inputed into the final fully connected layer. If this is confusing, review how the attention values are created at 12:58 - regardless of the number of input words, we add the scaled values together to get one sum per LSTM.

[@tangt304]

Another awesome video! Josh, will you plan to talk about BERT? Thank you!

[@statquest]

I'll keep that in mind.

[@JL-vg5yj]

super clutch my final is on thursday thanks a lot!

[@statquest]

Good luck!

[@shaktisd]

I have one fundamental question related to how attention model learns, so basically higher attention score is given to those pairs of word which have higher softmax (Q.K) similarity score. Now the question is how relationship in the sentence "The cat didn't climb the tree as it was too tall" is calculated and it knows that in this case "it" refers to tree and not "cat" . Is it from large content of data that the model reads helps it in distinguishing the difference ?

[@statquest]

Yes. The more data you have, the better attention is going to work.

[@umutnacak]

Great videos! So after watching technical videos I think complicating the math has no effect on removing bias from the model. In the future one can find a model with self-encoder-soft-attention-direct-decoder you name it, but it's still garbage in garbage out. Do you think there is a way to plug a fairness/bias filter to the layers so instead of trying to filter the output of the model you just don't produce unfair output? It's like preventing a disease instead of looking for a cure. Obviously I'm not an expert and just trying to get a direction for my personal ethics research out of this naive question. Thanks!

[@statquest]

To be honest, I'm super sure I understand what you are asking about. However, I know that there is something called "constitutional AI" that you might be interested in.

[@umutnacak]

@@statquest Thanks for the reply. OK this looks promising. Actually they already have a model called Claude. Not sure this is the thing I'm looking for or not, but at least a direction for me to look further into. Thanks again!

[@mrstriker1847]

Please add to the neural network playlist! Or don't it's your video, I just want to be able to find it when I'm looking for it to study for class.

[@statquest]

I'll add it to the playlist, but the best place to find my stuff is here: statquest.org/video-index/

[@elmehditalbi8972]

Could you do a video about Bert? Architectures like these can be very helpful on NLP and I think a lot of folks will benefit from that :)

[@statquest]

I've got a video on transformers coming out soon.

[@michaelbwin752]

Thank you for this explanation. But my question is how with backprogation are the weights and bias adjusted in such a model like this. if you could explain that i would deeply appreciate it.

[@statquest]

Backpropagation works for models like this just like it works for simpler models. You just use a whole lot of Chain Rule to calculate the derivatives of the loss function (which is cross entropy in this case) with respect to each weight and bias. To learn more about backpropagation, see: kzbin.info/www/bejne/f3-ViaB4na5_qpY kzbin.info/www/bejne/n6rRY62adrGcn5o and kzbin.info/www/bejne/fXy9oIJ-jayWgtE To learn more about cross entropy, see: kzbin.info/www/bejne/bHLVhKypatZ7d7c and kzbin.info/www/bejne/rnOomWlsi56akNE

[@seifeddineidani3256]

Thanks josh, great video! ❤I hope you upload the transformer video soon :)

[@statquest]

Coming soon!

[@guillermosainzzarate5110]

Y ahora en español? Casi no lo creo, este canal es increible😭 muchas gracias por tus videos !!!

[@statquest]

Muchas gracias! :)

[@RafaelRabinovich]

To really create a translator model, we would have to work a lot through values of linguistics since there are differences in word order, verb conjugation, idioms, etc. Going from one language to another is a big structural challenge for coders.

[@statquest]

That's the way they used to do it - by using linguistics. But very few people do it that way anymore. Now pretty much all translation is done with transformers (which are just encoder-decoder networks with attention, but not the LSTMs). Improvements in translation quality are gained simply by adding more layers of attention and using larger training datasets. For more details, see: en.wikipedia.org/wiki/Natural_language_processing

[@automatescellulaires8543]

wow, i didn't think i would see this kind of stuff on this channel.

[@statquest]

:)

[@frogloki882]

Another BAM!

[@statquest]

Thanks!

[@nogur9]

Thank you very much!

[@statquest]

You're welcome!

[@Thepando20]

Hi, great video SQ as always! I had the same question as @manuelcortes1835 and I understand that the encodings are the LSTM outputs. However, in 9:02 the outputs are 0.91 and 0.38, maybe I am missing something here?

[@statquest]

Yes, and at 13:36 they are rounded to the nearest 10th so they can fit in the small boxes. Thus 0.91 is rounded to 0.9 and 0.38 is rounded to 0.4.

[@Thepando20]

Thank you, all clear!

[@kaixuan5236]

Can you do videos on transformer network and multi-head attention? Love your vids!

[@statquest]

I'm working on it.

[@Sarifmen]

13:15 so the attention for EOS is just 1 number (per LSTM cell) which combines references to all the input words?

[@statquest]

Yep.

[@Fahhne]

Nice video, can't wait for the video about transformers (I imagine it will be the next one?)

[@statquest]

Yes, soon!

[@sagardesai1253]

great video thanks

[@statquest]

Thanks!

[@lakshaydulani]

now thats what i was looking for

[@statquest]

bam! :)