Тёмный

Transformers for beginners | What are they and how do they work 

AssemblyAI
Подписаться 135 тыс.
Просмотров 147 тыс.
50% 1

This week we’re looking into transformers. Transformers were introduced a couple of years ago with the paper Attention is All You Need by Google Researchers. Since its introduction transformers has been widely adopted in the industry.
Get your Free Token for AssemblyAI Speech-To-Text API 👇
www.assemblyai.com/?...
Models like BERT, GPT-3 made groundbreaking improvements in the world of NLP using transformers. Since then model libraries like hugging face made it possible for everyone to use transformer based models in their projects. But what are transformers and how do they work? How are they different from other deep learning models like RNNs, LSTMs? Why are they better?
In this video, we learn about it all!
Some of my favorite resources on Transformers:
The original paper - arxiv.org/pdf/1706.03762.pdf
If you’re interested in following the original paper with the code - nlp.seas.harvard.edu/2018/04/0...
The Illustrated Transformer - jalammar.github.io/illustrate...
Blog about positional encodings - kazemnejad.com/blog/transform...
About attention - Visualizing A Neural Machine Translation Model - jalammar.github.io/visualizin...
Layer normalization - arxiv.org/abs/1607.06450
Some images used in this video are from:
colah.github.io/posts/2015-08...
jalammar.github.io/visualizin...
/ how-to-easily-build-a-...
/ elegant-intuitions-beh...

Опубликовано:

 

17 июн 2024

Поделиться:

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист
Посмотреть позже
Комментарии : 143   
@pierluigiurru962
@pierluigiurru962 8 месяцев назад
This is clearest explanation of transformers I’ve found so far, and I personally have seen many trying to wrap my head around them. No skimming over details. Very well done!
@ashermai2962
@ashermai2962 2 года назад
This channel deserves more views and likes
@AssemblyAI
@AssemblyAI 2 года назад
Thank you Asher!
@sarc007
@sarc007 Год назад
I agree
@Yaddu143
@Yaddu143 Год назад
I really want you talk about attention. Thank you, shinning in this video.
@moeal5110
@moeal5110 9 месяцев назад
This is most clear and resourceful video I've seen. Thank you for your hard work and for sharing these resources
@reshamgaire4188
@reshamgaire4188 9 месяцев назад
Finally found a perfect video that cleared all my confusions. Thank you so much ma'am, may god bless you 🙏
@dooseobkim2100
@dooseobkim2100 11 месяцев назад
You are my savior for being actually able to get ready to read all of those AI related papers which I’m completely unaware of. I was stuck at the part of my thesis which I have to provide theoretical background of ChatGPT. As a business student I’m super grateful to learn these knowledges in computer science through your short lecture👍👍
@yourshanky
@yourshanky Год назад
Excellent explanation !! Sharp and clear. Thanks for sharing this.
@testing3562
@testing3562 6 месяцев назад
I am a programmer, I have created many tools that were actually very useful. I even claim that I have 10+ years experience. But I feel very bad to realize that I am so dumb that I did not understand anything after the first 10 minutes of the video.
@sebastianmata9603
@sebastianmata9603 2 месяца назад
They explain it with apples and pears but is actually a very mathematical and elaborated process, if you're not the kind of person that can remember easily how work the sine and cosine functions and do matrix multiplication for fun, is just a little bit harder to get it
@moonlight-td8ed
@moonlight-td8ed Месяц назад
BRUH JUST REWATCH IT AGAIN... THE VIDEO IS A 10/10
@bdoriandasilva
@bdoriandasilva Год назад
Great video with a clear explanation. thank you!
@sivad2895
@sivad2895 9 месяцев назад
The best video on transformer architecture with great explanations and charming presentation.
@nikhilshrestha4711
@nikhilshrestha4711 Год назад
really love how you described the model. easier to understand 🙌
@AssemblyAI
@AssemblyAI Год назад
Glad it was helpful!
@mohamadhasanzeinali3674
@mohamadhasanzeinali3674 Год назад
I saw numerous videos about Transformers architecture. In my opinion, your video is the best among them. Appreciate that.
@AssemblyAI
@AssemblyAI Год назад
Thank you, that is great to hear. :)
@anandanv2361
@anandanv2361 Год назад
The way you explained the concept was awesome. It is very easy to follow.👍
@moonlight-td8ed
@moonlight-td8ed Месяц назад
cleanest and most informative video ever.. covered whole attention is all you need paper in 19 mins.. damn.. thank you MISRA TURP and assembly ai
@dannown
@dannown Год назад
This is a really lovely video -- very specific and detailed, but also followable. Thanks!
@AssemblyAI
@AssemblyAI Год назад
Glad it was helpful!
@nikhil182
@nikhil182 Год назад
Thank you so much!💓this has to be the best introduction video to Transformers. We are planning to use Transformers for our Video Processing project.
@AssemblyAI
@AssemblyAI Год назад
Glad it was helpful!
@GeorgeZoto
@GeorgeZoto 9 месяцев назад
Great and both low and high level descprition of transformers, thank you for creating this useful resource :)
@otsogileonalepelo9610
@otsogileonalepelo9610 Год назад
Just WOW! You broke down these concepts nicely. Thank you. Live long and prosper 🖖🖖
@AssemblyAI
@AssemblyAI Год назад
Thank you!
@kalyandey5195
@kalyandey5195 4 месяца назад
Awesome!! crystal clear explanation!!!
@mudasserqayyom9947
@mudasserqayyom9947 Месяц назад
I'm watching lot of videos of Transformers, But that is exactly I want. Thank You So Much Ma'am. And also AssemblyAl.
@pyaephyo3633
@pyaephyo3633 11 месяцев назад
i love it. Your explanation is easy to understand.
@abinav92
@abinav92 Год назад
Best video on intro to transformers!!!
@goelnikhils
@goelnikhils Год назад
Amazing Explanation. Vow. Thanks a lot
@carlosroquesuarezgurruchag8681
Thx for the time. Very clear the explanation
@imagnihton2
@imagnihton2 Год назад
This made the concept sound incredibly simple compared to some other sources... Amazing!
@AssemblyAI
@AssemblyAI Год назад
Great to hear, thank you!
@sanketdeshmukh491
@sanketdeshmukh491 Год назад
Thank You for in depth explanation. Kudos!!!
@AssemblyAI
@AssemblyAI Год назад
You're very welcome!
@geekyprogrammer4831
@geekyprogrammer4831 Год назад
This high quality video deserves a lot more views!
@AssemblyAI
@AssemblyAI Год назад
Thank you!
@PeterKoman
@PeterKoman Год назад
Finally a transformer video that actually explains the theory in understandable way. Many thanks.
@AssemblyAI
@AssemblyAI Год назад
That's great to hear, thank you Peter!
@malayali_thaaram
@malayali_thaaram Год назад
Yes!!! I agree! Finally!
@stevemassicotte4068
@stevemassicotte4068 Год назад
@16:14,, the binary table is wrong, there are two sevens. The second column should start with 8 and not a second 7. Attention is all you need ;) Thanks for the video !
@BCSEbadulIslam
@BCSEbadulIslam 4 месяца назад
Came here to comment the same 👍
@vivekpetrolhead
@vivekpetrolhead 6 месяцев назад
Best explanation for beginners I've seen besides statquest
@maryammoradbeigi6690
@maryammoradbeigi6690 Год назад
Incredible explanation on the transformer... Amazing video. Thanks a lot
@AssemblyAI
@AssemblyAI Год назад
Glad you liked it!
@amitsingh7684
@amitsingh7684 Месяц назад
very nicely explained with clear details
@Zulu369
@Zulu369 Год назад
This video is the best technical explanation I have seen in years. Although Transformers are a breakthrough in the field in NLP, I am convinced that they do not describe completely and satisfactorily, the way humans process language. For all civilizations, spoken language predates written language in communications. Those who do not read and write, still communicate clearly with others. This means humans do not represent natural language in their brains in terms of words, syntax and position of tokens but rather in terms of symbols, images and multimedia shows that make up stories we relate to. Written language comes only later as an extra layer of communication to express transparently these internal representations that we carry within ourselves. If AI is able to access and decode these internal representations, then the written language, the extra layer, becomes a lot easier to understand, organize, and put on paper with simple techniques rather than using these intricate Transformers that I consider as temporary and unnatural ways of describing natural languages.
@rokljhui864
@rokljhui864 Год назад
Your idea is represented above , in words, existing separately from your mind. Surely most intelligence is contained within written language, mathematical expression and images.
@Zulu369
@Zulu369 Год назад
@@rokljhui864 As I explained above, written words make up THE extra layer that is actually not necessary once you learn more persuasive communications techniques.
@evetsnilrac9689
@evetsnilrac9689 7 месяцев назад
​@@rokljhui864 "Surely" is not how you start an intelligent hypothesis. You must explain the rationale for your belief since it is not at all readily apparent that the intelligence to process written language was not already in our brains so that we could conceive of and learn written language.
@evetsnilrac9689
@evetsnilrac9689 7 месяцев назад
This is a crucial point to understand for all of us interested in fully harnessing what we perceive to be the true potential of this technology. I would start with the Adamic symbol-based language.
@hussainsalih3520
@hussainsalih3520 Год назад
amazing keep doing this amazing tutorials :)
@shubham-pp4cw
@shubham-pp4cw 2 года назад
clear explanation of quiet complex topic and explained easily in shorted period time
@AssemblyAI
@AssemblyAI 2 года назад
Glad to hear you liked it!
@wasifrock687
@wasifrock687 Год назад
very well explained. thank you!
@AssemblyAI
@AssemblyAI Год назад
Glad it was helpful!
@_joshwalter_
@_joshwalter_ 11 месяцев назад
This is phenomenal!
@andybrice2711
@andybrice2711 2 месяца назад
Positional encodings are not that weird when you think of them as being similar to the hands on a clock: It's a way of representing arbitrarily long periods of time, within a confined space, with smooth continuous movement and no sudden jumps. Picture the tips of clock hands. Their vertical position follows a sine wave, their horizontal position follows a cosine wave. And we add precision with more hands moving at different speeds.
@amigospot
@amigospot 2 года назад
Nice video for a fairly complex architecture!
@AssemblyAI
@AssemblyAI 2 года назад
Thanks Hyder! - Mısra
@jayanthkothapalli9.2
@jayanthkothapalli9.2 11 месяцев назад
Great work mam. You made it simple to understand.
@archowdhury007
@archowdhury007 11 месяцев назад
Beautifully explained. Loved it. First time I understood the transformer model so easily. Great work. Please keep creating more such content. Thanks.
@VaibhavPatil-rx7pc
@VaibhavPatil-rx7pc 11 месяцев назад
smile and learn and clean explaniation!!!
@krishnakumarik208
@krishnakumarik208 7 месяцев назад
VERY GOOD EXPLANATION.
@keithwins
@keithwins 5 месяцев назад
Thank you that was excellent
@bysedova
@bysedova 9 месяцев назад
Please make a detailed video about self-attantion! Thank you for your explanation! I like you haven't used difficult math terms and you have tried to explain for understanding with easy material supply.
@AddisuSeteye
@AddisuSeteye Год назад
Amazing explanation. I can't wait to watch your explanation on another AI related topic.
@AssemblyAI
@AssemblyAI Год назад
More to come!
@thebiggerpicture__
@thebiggerpicture__ Год назад
Great video. Thanks!
@AssemblyAI
@AssemblyAI Год назад
You're welcome :)
@rodi4850
@rodi4850 Год назад
best explanation!
@nikbl4k
@nikbl4k 16 дней назад
great video, very interesting
@juliennoel3061
@juliennoel3061 4 месяца назад
hi! oh yeah please a specific video on 'attention' 🙂 - And also : 'great job you are doing! Congrats! Thumbs !!'
@devraj241
@devraj241 Год назад
great video, well explained!
@near_.
@near_. Год назад
What's the purpose of output embedding?? What are we feeding in that???
@JayTheMachine
@JayTheMachine 9 месяцев назад
thank you soo much, damn, love your explainations
@donevo1
@donevo1 Год назад
very nice presentation! in 12:18 you say that attention is on 8 words. from reading the paper I think that attention is on ALL the words, and 8 is the number of heads: each word vector (D=512) is split to 8, i.e vector dimention in each head is 64.
@6001navi
@6001navi 11 месяцев назад
awesome explanation
@user-fp5sx2vr4z
@user-fp5sx2vr4z Год назад
Thank you for the presentation, it has been so insightful. I wish you made a video about the word embeddings of the transformers. Thanks
@AssemblyAI
@AssemblyAI Год назад
Great suggestion!
@MrTheyosyos
@MrTheyosyos Год назад
"attentions for beginners" will be great :)
@0Tyr
@0Tyr 2 года назад
Very informative channel, and well presented..
@AssemblyAI
@AssemblyAI 2 года назад
Thank you! - Mısra
@niyatisrivastava4-yearb.te820
@niyatisrivastava4-yearb.te820 6 месяцев назад
best explanation
@talktovipin1
@talktovipin1 4 месяца назад
Very nice explanation. Incorporating animations into the images while explaining would enhance comprehension and make it even more beneficial.
@salamander7715
@salamander7715 9 месяцев назад
Seeing all the comments of people saying that this video made things simple just makes me feel stupid ahah! This video is amazing and the explanations are great, but i can't say i've understood more then 35% of the concepts. I'll have to watch this several times for sure
@rufus9322
@rufus9322 Год назад
Thank you for your video 🤗 How to understanding more details about word embedding method in Transformer model?
@nogur9
@nogur9 11 месяцев назад
Thanks :)
@kartikgadad9285
@kartikgadad9285 7 месяцев назад
Thanks for explaining Transformers, can we have a video on Embeddings, seems super interesting. The Positional Encoding part was difficult to understand, as it has been just taken from abstract level, can we find better video on positional encoding?
@user-ft2jx8io9g
@user-ft2jx8io9g 9 месяцев назад
geart work, may allah bless you and guide you 🥰🥰😍😍
@wenshufan
@wenshufan Год назад
Thank you for explaining the transformer in detail. However, I still don't get how do you train the Q,K,V matrix. The attention mechanism is calculated by from them. What type of feedback/truth can one use to train those matrix values then?
@andersonsystem2
@andersonsystem2 2 года назад
Good video
@AssemblyAI
@AssemblyAI 2 года назад
Glad you enjoyed it :)
@actorjohanmatsfredkarlsson2293
Great video. I’m missing how the attation layers: queries, keys and values and the output weights are trainee? Also what was the values matrix for?
@MrAmgadHasan
@MrAmgadHasan Год назад
They are trained just like any neural network: we have a loss function that compares the model's output with the desired output, and then this loss is propagated backwards to the weights and biases and we use gradient descent to update the weights. Lookup "back propagation" for more info or just look up"how neural networks are trained"
@rokljhui864
@rokljhui864 Год назад
Interesting. Sounds like a Fourier transform; Obtaining a frequency distribution from a time-series, reveals the underlying frequency components and amplitudes. Are you essentially distilling the 'word cycles' from the sentences to obtain meaning from the word patterns across different word combination lengths (from single word to many thousand) And, optimising the predictability of the next word automatically optimises for the appropriate word combination lengths, that align with actual meaning. i.e Understanding 'peaks' are optimised similar to the fundamental frequencies in a Fourier transform. ?
@RAZZKIRAN
@RAZZKIRAN Год назад
thank u
@AssemblyAI
@AssemblyAI Год назад
You're welcome!
@user-tt6tg3eb7n
@user-tt6tg3eb7n 8 месяцев назад
I overall liked the video a lot. I just do not thing is enough to understand the whole concept. Especially masked multi head attention layer was missing and how the actually outcome of the model is created (translation etc)
@lexflow2319
@lexflow2319 Год назад
I don't understand why there are 6 decoders and encoders. The diagram shows 1 each. Also, what is the output as input to the decoder. Is that the last output from final softmax
@ankit9401
@ankit9401 2 года назад
You are awesome and I appreciate your efforts. After watching your video, I can say now I understand the transformer architecture. I have a query. According to original BERT paper, two objectives used during training: Masked Language Model and Next Sentence Prediction. Are these training objectives present in original or all transformer models or they are specifically used for BERT ? I hope you make video to explain attention and BERT model in future 😊
@AssemblyAI
@AssemblyAI 2 года назад
Great to hear the video was helpful Ankit! These are not the tasks that were in the original transformer model. But I think they are not specific to BERT. Other architectures also use same/similar tasks to train their models. We have a BERT video in the channel by the way. Here it is: ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-6ahxPTLZxU8.html - Mısra
@strongsyedaa7378
@strongsyedaa7378 2 года назад
@@AssemblyAI So instead of using RNN & LSTM we directly use Transformers?
@kellenswain2049
@kellenswain2049 Год назад
11:06 from reading the paper, 64 is not the square root of the length of QKV vectors, it looks like it is d_model/h where h is the number of heads used in multihead attention. And so then I assume d_model is the length of the QKV vectors?
@mbrochh82
@mbrochh82 Год назад
I wish someone would explain how exactly the backpropagation works and what values exactly get nudged and tweaked during learning (and by which means)
@abrahamowos
@abrahamowos Год назад
A question @ 11:30 : if for instance the values v are really large and you multiple them by the results from the softmax layer. Won't the resulting weighted be too high after adding them together?
@JackoMcW
@JackoMcW Год назад
I'm not sure I understand your question or what you mean by "too high," but consider that all of those softmax values will be
@helgefredriksen
@helgefredriksen 11 дней назад
Hi, could anyone explain how the Feed Forward part of the transformer learns? How does the loss function work? By masking out some of the input from the self-attention part during training and then compare the real value with predicted value?
@amparoconsuelo9451
@amparoconsuelo9451 9 месяцев назад
I have read books and watched videos on Transformers. I still don't understand Transformers. I want to order from Amazon an assembly Transformer kit, work on it and have a Transformer I understand the way I undestand how Lotus 123 and Wordstar were created.
@guimaraesalysson
@guimaraesalysson Год назад
Theres any video about attention mechanism ?
@AssemblyAI
@AssemblyAI Год назад
Not yet but it's a good idea!
@wp1300
@wp1300 Год назад
13:35 Positional encoding
@near_.
@near_. Год назад
What's the purpose of output embedding?? What are we feeding in that???
@near_.
@near_. Год назад
What's the purpose of output embedding?? What are we feeding in that???
@manjz7hm
@manjz7hm 5 месяцев назад
You explained well , but my brain not digesting it 😂
@user-bu3ds4dc6d
@user-bu3ds4dc6d 9 месяцев назад
easiest explanation.
@EmanueleOlivetti
@EmanueleOlivetti 6 месяцев назад
Around 16:00 the binary representation repeats twice 7 so the right part of the binary encoded numbers is incorrect
@nirmesh44
@nirmesh44 4 месяца назад
make attention video
@roshanverma1123
@roshanverma1123 11 месяцев назад
Great simplified content! Thanks! Btw, you look beautiful!
@titusfx
@titusfx Год назад
I'm still concern how all these papers don't have any mathematical rigour, there isn't one theorem, there is nothing. And it works....🤯 I can't imagine when the rigourosity start coming in, what would be the results. I'm starting to believe that deep learning is Physics for knowledge 😅
@robl39
@robl39 Год назад
What is disappointing about this video is that you have to know about or understand 50 other concepts first
@M7mdal7aj
@M7mdal7aj 9 месяцев назад
thanks but the explanation is not detailed enough. but nice explanation for the positional embedding. thanks
@marcfruchtman9473
@marcfruchtman9473 Год назад
Very interesting and informative. Thank you for providing a very detailed explanation of Transformers. One note: The word "Query" is pronounced like Qw-eerie (USA English). The beginning sounds sort of like the sound of "Quarry", or "Quack" but rhyming with dearie.
@NielsSwimberghe
@NielsSwimberghe 4 месяца назад
"You might need to watch this multiple times". You don't say. 😅
@denwo1982
@denwo1982 3 месяца назад
Chatgpt “explain this video to me as if I was an 8 year old”
@JaredEdwardsPM
@JaredEdwardsPM Год назад
I feel like you just described how a ouija board works…
@AssemblyAI
@AssemblyAI Год назад
Comment of the year :D
@frizzsupertramp6434
@frizzsupertramp6434 Год назад
At 16:44 the binary representations on the right side are wrong (number 7 comes twice, should start with 8 on the right side). (Sorry for being anal 😀)
@AssemblyAI
@AssemblyAI Год назад
Thanks for the heads up! Video editing gets tedious sometimes :)
@strongsyedaa7378
@strongsyedaa7378 2 года назад
Why YOU divided by 8?
@prdeshnaser5297
@prdeshnaser5297 4 месяца назад
needs pauses in speech, after 15min all i hear is a vector of blblblahs. a good video and human illustration of how text gets generated by machines, but that is not the point.
@homeboundrecords6955
@homeboundrecords6955 Год назад
knowledgable but not exactly 'beginner' level lol
@AssemblyAI
@AssemblyAI Год назад
To some it sounds too simple and to some too complex. 🤷‍♀️ Problem with AI topics these days. :D
@open_source
@open_source Год назад
The presentation is nice but are you really trying to compress video time by talking faster? Had to stop the video multiple times to Focus on each concept
@sevovo
@sevovo 11 месяцев назад
Why is the first think I thought is that she must be Turkish? :D
@verystablegenius4720
@verystablegenius4720 9 месяцев назад
bad ... just bad. you need to put 100X the time if you want to do this right. No real understanding here.
@dlbattle100
@dlbattle100 Год назад
Carry, kiw, and matresses.
Далее
What is Transfer Learning? | With code in Keras
10:52
World’s Deadliest Obstacle Course!
28:25
Просмотров 73 млн
Transformers explained | The architecture behind LLMs
19:48
Attention Is All You Need
27:07
Просмотров 618 тыс.
AI Language Models & Transformers - Computerphile
20:39