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

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...

[@ashermai2962]

This channel deserves more views and likes

[@AssemblyAI]

Thank you Asher!

[@sarc007]

I agree

[@pierluigiurru962]

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!

[@testing3562]

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]

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]

BRUH JUST REWATCH IT AGAIN... THE VIDEO IS A 10/10

[@andybrice2711]

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.

[@stevemassicotte4068]

@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]

Came here to comment the same 👍

[@dooseobkim2100]

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👍👍

[@PeterKoman]

Finally a transformer video that actually explains the theory in understandable way. Many thanks.

[@AssemblyAI]

That's great to hear, thank you Peter!

[@malayali_thaaram]

Yes!!! I agree! Finally!

[@mudasserqayyom9947]

I'm watching lot of videos of Transformers, But that is exactly I want. Thank You So Much Ma'am. And also AssemblyAl.

[@moonlight-td8ed]

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

[@moeal5110]

This is most clear and resourceful video I've seen. Thank you for your hard work and for sharing these resources

[@bdoriandasilva]

Great video with a clear explanation. thank you!

[@Yaddu143]

I really want you talk about attention. Thank you, shinning in this video.

[@reshamgaire4188]

Finally found a perfect video that cleared all my confusions. Thank you so much ma'am, may god bless you 🙏

[@nikhilshrestha4711]

really love how you described the model. easier to understand 🙌

[@AssemblyAI]

Glad it was helpful!

[@Zulu369]

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]

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]

@@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]

​@@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]

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.

[@yourshanky]

Excellent explanation !! Sharp and clear. Thanks for sharing this.

[@anandanv2361]

The way you explained the concept was awesome. It is very easy to follow.👍

[@sivad2895]

The best video on transformer architecture with great explanations and charming presentation.

[@imagnihton2]

This made the concept sound incredibly simple compared to some other sources... Amazing!

[@AssemblyAI]

Great to hear, thank you!

[@mohamadhasanzeinali3674]

I saw numerous videos about Transformers architecture. In my opinion, your video is the best among them. Appreciate that.

[@AssemblyAI]

Thank you, that is great to hear. :)

[@dannown]

This is a really lovely video -- very specific and detailed, but also followable. Thanks!

[@AssemblyAI]

Glad it was helpful!

[@otsogileonalepelo9610]

Just WOW! You broke down these concepts nicely. Thank you. Live long and prosper 🖖🖖

[@AssemblyAI]

Thank you!

[@nikhil182]

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]

Glad it was helpful!

[@amitsingh7684]

very nicely explained with clear details

[@GeorgeZoto]

Great and both low and high level descprition of transformers, thank you for creating this useful resource :)

[@abinav92]

Best video on intro to transformers!!!

[@carlosroquesuarezgurruchag8681]

Thx for the time. Very clear the explanation

[@kalyandey5195]

Awesome!! crystal clear explanation!!!

[@vivekpetrolhead]

Best explanation for beginners I've seen besides statquest

[@geekyprogrammer4831]

This high quality video deserves a lot more views!

[@AssemblyAI]

Thank you!

[@goelnikhils]

Amazing Explanation. Vow. Thanks a lot

[@sanketdeshmukh491]

Thank You for in depth explanation. Kudos!!!

[@AssemblyAI]

You're very welcome!

[@shubham-pp4cw]

clear explanation of quiet complex topic and explained easily in shorted period time

[@AssemblyAI]

Glad to hear you liked it!

[@bysedova]

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.

[@_joshwalter_]

This is phenomenal!

[@pyaephyo3633]

i love it. Your explanation is easy to understand.

[@hussainsalih3520]

amazing keep doing this amazing tutorials :)

[@maryammoradbeigi6690]

Incredible explanation on the transformer... Amazing video. Thanks a lot

[@AssemblyAI]

Glad you liked it!

[@donevo1]

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.

[@rodi4850]

best explanation!

[@abrahamowos]

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]

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

[@AddisuSeteye]

Amazing explanation. I can't wait to watch your explanation on another AI related topic.

[@AssemblyAI]

More to come!

[@wasifrock687]

very well explained. thank you!

[@AssemblyAI]

Glad it was helpful!

[@VaibhavPatil-rx7pc]

smile and learn and clean explaniation!!!

[@salamander7715]

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

[@wenshufan]

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?

[@krishnakumarik208]

VERY GOOD EXPLANATION.

[@amigospot]

Nice video for a fairly complex architecture!

[@AssemblyAI]

Thanks Hyder! - Mısra

[@MrTheyosyos]

"attentions for beginners" will be great :)

[@keithwins]

Thank you that was excellent

[@juliennoel3061]

hi! oh yeah please a specific video on 'attention' 🙂 - And also : 'great job you are doing! Congrats! Thumbs !!'

[@jaysoni6674]

thank you soo much, damn, love your explainations

[@user-fp5sx2vr4z]

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]

Great suggestion!

[@lexflow2319]

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

[@thebiggerpicture__]

Great video. Thanks!

[@AssemblyAI]

You're welcome :)

[@rufus9322]

Thank you for your video 🤗 How to understanding more details about word embedding method in Transformer model?

[@jayanthkothapalli9.2]

Great work mam. You made it simple to understand.

[@talktovipin1]

Very nice explanation. Incorporating animations into the images while explaining would enhance comprehension and make it even more beneficial.

[@niyatisrivastava4-yearb.te820]

best explanation

[@devraj241]

great video, well explained!

[@near_.]

What's the purpose of output embedding?? What are we feeding in that???

[@6001navi]

awesome explanation

[@0Tyr]

Very informative channel, and well presented..

[@AssemblyAI]

Thank you! - Mısra

[@archowdhury007]

Beautifully explained. Loved it. First time I understood the transformer model so easily. Great work. Please keep creating more such content. Thanks.

[@kartikgadad9285]

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?

[@nogur9]

Thanks :)

[@rokljhui864]

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. ?

[@amparoconsuelo9451]

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.

[@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]

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"

[@user-ft2jx8io9g]

geart work, may allah bless you and guide you 🥰🥰😍😍

[@user-tt6tg3eb7n]

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)

[@manjz7hm]

You explained well , but my brain not digesting it 😂

[@ankit9401]

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]

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: kzbin.info/www/bejne/bJLLqYOKgb-ri5o - Mısra

[@strongsyedaa7378]

@@AssemblyAI So instead of using RNN & LSTM we directly use Transformers?

[@kellenswain2049]

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]

I wish someone would explain how exactly the backpropagation works and what values exactly get nudged and tweaked during learning (and by which means)

[@near_.]

What's the purpose of output embedding?? What are we feeding in that???

[@guimaraesalysson]

Theres any video about attention mechanism ?

[@AssemblyAI]

Not yet but it's a good idea!

[@wp1300]

13:35 Positional encoding

[@near_.]

What's the purpose of output embedding?? What are we feeding in that???

[@EmanueleOlivetti]

Around 16:00 the binary representation repeats twice 7 so the right part of the binary encoded numbers is incorrect

[@RAZZKIRAN]

thank u

[@AssemblyAI]

You're welcome!

[@andersonsystem2]

Good video

[@AssemblyAI]

Glad you enjoyed it :)

[@titusfx]

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 😅

[@nirmesh44]

make attention video

[@M7mdal7aj]

thanks but the explanation is not detailed enough. but nice explanation for the positional embedding. thanks

[@user-bu3ds4dc6d]

easiest explanation.

[@NielsSwimberghe]

"You might need to watch this multiple times". You don't say. 😅

[@denwo1982]

Chatgpt “explain this video to me as if I was an 8 year old”

[@JaredEdwardsPM]

I feel like you just described how a ouija board works…

[@AssemblyAI]

Comment of the year :D

[@marcfruchtman9473]

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.

[@frizzsupertramp6434]

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]

Thanks for the heads up! Video editing gets tedious sometimes :)

[@robl39]

What is disappointing about this video is that you have to know about or understand 50 other concepts first

[@roshanverma1123]

Great simplified content! Thanks! Btw, you look beautiful!

[@prdeshnaser5297]

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.

[@strongsyedaa7378]

Why YOU divided by 8?

[@homeboundrecords6955]

knowledgable but not exactly 'beginner' level lol

[@AssemblyAI]

To some it sounds too simple and to some too complex. 🤷‍♀️ Problem with AI topics these days. :D

[@verystablegenius4720]

bad ... just bad. you need to put 100X the time if you want to do this right. No real understanding here.

[@open_source]

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]

Why is the first think I thought is that she must be Turkish? :D

[@dlbattle100]

Carry, kiw, and matresses.

[@berkk1993]

Idk who she is but I am sure she is Turkish.

[@PrabhatKumar-fn4vy]

You are beautiful