Transformers, explained: Understand the model behind GPT, BERT, and T5
Vložit
- čas přidán 4. 06. 2024
- Dale’s Blog → goo.gle/3xOeWoK
Classify text with BERT → goo.gle/3AUB431
Over the past five years, Transformers, a neural network architecture, have completely transformed state-of-the-art natural language processing. Want to translate text with machine learning? Curious how an ML model could write a poem or an op ed? Transformers can do it all. In this episode of Making with ML, Dale Markowitz explains what transformers are, how they work, and why they’re so impactful. Watch to learn how you can start using transformers in your app!
Chapters:
0:00 - Intro
0:51 - What are transformers?
3:18 - How do transformers work?
7:41 - How are transformers used?
8:35 - Getting started with transformers
Watch more episodes of Making with Machine Learning → goo.gle/2YysJRY
Subscribe to Google Cloud Tech → goo.gle/GoogleCloudTech
#MakingwithMachineLearning #MakingwithML
product: Cloud - General; fullname: Dale Markowitz; re_ty: Publish; - Věda a technologie
Ability to break down complex topic is such an underrated super power. Amazing job.
Transformers! More than meets the eye.
😂
Transformers! Robots in disguise!
Autobots wage their battle to fight the evil forces of the Decepticons!!!!!
Transformers! No money to buy…
Oczywiście
How did you condense so many pieces of information in such a short time? This video is on a next level, I loved it!
This is awesome. This has been one of the best overall breakdowns I've found. Thank you!!
Great explanation of the key concept of position encoding and self attention. Amazing you get the gist covered in less than 10 minutes.
@Dino Sauro tell me more...
@Dino Sauro thanks for the heads up
She has one of the wealthiest company on earth providing her resources. First hand access to engineers, researchers, top notch communicators and marketing employees.
@@an-dr6eu True, but this young lady talks a mile-a-minute from memory. She's knows it cold regardless of the resources at Google.
@@michaellavelle7354 Her explanation is absolutely useless. Have you ever programmed a Transformer model from scratch to verify what she has explained?
This is such an informative video about transformers in machine learning! It's amazing how a type of neural network architecture can do so much, from translating text to generating computer code. I appreciate the clear explanations of the challenges with using recurrent neural networks for language analysis, and how transformers have overcome these limitations through innovations like positional encodings and self-attention. It's also fascinating to hear about BERT, a popular transformer-based model that has become a versatile tool for natural language processing in many different applications. The tips on where to find pertrained transformer models and the popular transformers Python library are super helpful for anyone looking to start using transformers in their own app. Thanks for sharing this video!
This is a really awesome video! Thank you so much for simplyifying the concepts.
You have the gift of making things simple to understand. Keep up the good work 🙏
Amazing video! Nice explanation and examples 😄👍
I would like to see more videos like this and practices ones
Dale you are so good at explaining this tech, thank you!
Thanks you did a great job. I spent some time already looking at different videos to capture the high level idea of what transformers are about and yours is the clearest explanation. I actually do have an educational background in neutral networks but don't go around remembering every details or the state of the art today so somebody removing all the unessesary technical details like you did here is very useful.
I loved it and very simple ,clear explanation.
So easy and clear to understand. Thanks
Takeaways:
A transformer is a type of neural network architecture that is used in natural language processing. Unlike recurrent neural networks (RNNs), which analyze language by processing words one at a time in sequential order, transformers use a combination of positional encodings, attention, and self-attention to efficiently process and analyze large sequences of text.
Neural networks, Convolutional neural networks (for image analysis), Recurrent neural networks (RNNs), Positional encodings, Attention, Self-attention
Neural networks: A type of model used for analyzing complicated data, such as images, videos, audio, and text.
Convolutional neural networks: A type of neural network designed for image analysis.
Recurrent neural networks (RNNs): A type of neural network used for text analysis that processes words one at a time in sequential order.
Positional encodings: A method of storing information about word order in the data itself, rather than in the structure of the network.
Attention: A mechanism used in neural networks to selectively focus on parts of the input.
Self-attention: A type of attention mechanism that allows the network to focus on different parts of the input simultaneously.
Neural networks are like a computerized version of a human brain, that uses algorithms to analyze complex data.
Convolutional neural networks are used for tasks like identifying objects in photos, similar to how a human brain processes vision.
Recurrent neural networks are used for text analysis, and are like a machine trying to understand the meaning of a sentence in the same order as a human would.
Positional encodings are like adding a number to each word in a sentence to remember its order, like indexing a book.
Attention is like a spotlight that focuses on specific parts of the input, like a person paying attention to certain details in a conversation.
Self-attention is like being able to pay attention to multiple parts of the input at the same time, like listening to multiple conversations at once.
Great, you learned how to copy paste
@@an-dr6eu first step on becoming a programmer
@@an-dr6eu your comment comes over somewhat 'catty' 😢
i really enjoyed the concepts you explained. simple to understand
Positional Encoding, Attention and Self Attention. That's it! Really well summarized.
Love how you simplified it. Thank you
It s so simplified that you can t understand anything
Charm, intelligence and clarity! Thanks!
Wow, this is so well explained.
This is a GREAT explanation! please lower the background music next time it could really help. thanks again! awesome video
Such a simple yet revolutionary 💡idea
I love how to simplify something so complex, thank you so much Dale, the explanation was perfect
how did you do that
@@asstimus-prime This one? Just type ":" (colon) followed by "thanksdoc" and end it with another colon. I can add other emojis like 🤟too!
@@nahiyanalamgir7056 it needs desktop CZcams i think
@@asstimus-prime Apparently, it does. When will these apps be consistent across devices and platforms?
@@nahiyanalamgir7056 thanks though
Very well explained.. This really is a high level view of what Transformers are, but it's probably enough to just get your toes wet in the field!
That's a really good high-level explanation!
Fantastic!. Thanks for simplifying the concept
Where is optimus prime?
He's on the thumbnail...
He will be in theaters in June 9... Transformers : Rise of breasts..
😂😂😂😂
Where are robotaxis?
We got lied to
Hi Google! First of all, thank you for this wonderful video. I'm working on a multiclass (single label) supervised learning that uses Bert for transfer learning. I've got about 10 classes and a couple hundred thousand examples. Any tips on best practices (which Bert variants to use, what order of magnitude of dropout to use if any)? I know I could do hyperparameter search but that'd probably cost more time and money than I'm comfortable with (for a prototype), so I'm looking to make the most out of my local Nvidia 3080.
This was a really, really awesome breakdown 👏🏾
Amazing video! 🎉 You explained that difficult concepts of Transformers so clearly and made it easy to understand. Thanks for all your hard work!🙌👍
Are you serious? The concepts were not really explained. Just a summary of what they do but not how they work behind the scenes.
No.
Love the content and thanks for the great video! (one thing that might help is lower the background music a bit, I found myself stopping the video because I thought another app was playing music)
Thank you so much. I really needed this video, other videos were just confusing
This has to be the best explanation so far, and by a very large margin.
Thank you for watching! We appreciate the kind words. 🤗
Very interesting, informative, this added perspective to a hyped-up landscape. I'll admit, I'm new to this, but when I hear "pretrained transformer" I didn't even think about BERT. I appreciate getting the view from 10,000 feet.
This is a very well produced video. Credits to the presenter and those involved in production with the graphics
This is one of the best vids I've watched on this topic!
Nice amount of info parted in this video. Very clear info on what Transformers are and what made them so great.
Thanks for your hard work.This video is very helpful!!!
I have more respect for Google after watching this Video. Not only did they provided their engineers with the funding to research, but they also let other companies like OpenAI to use said research. And they are opening up the knowledge for the general public with these video series.
Simply loved it!
thank you! I'm just starting to learn about gpt and this was quite helpful, though I will have to watch it again :)
Excellent presentation and explanation of concepts
This is an excellent video introduction for transformers.
Informative! Thank you
crazy how things have changed so much
Thanks Ma'am. You broke it down well.
Amazing explanation!
super well done. Thanks for this!
so super helpful for my thesis, thank u
Easiest to understand explaination ive heard so far
Very good lecture, thanks!
I knew little on transformers before this video. I know little on transformers after this video. But I guess in order to know some, we'll need a 2-3 hours video.
Great video. Thank you!
The visuals are very helpful. Thanks.
You're very welcome!
wow, what a great summary! thanks!!!
Great video for people who are curious but don’t really want to (or can’t) understand how transformers actually work.
You have no idea how much time I potentially have saved just by reading your blog and watching this video to get me up to speed quickly on this. "Liked" this video. Thanks
do transformers learn the internal representation one language at a time or all of them at the same time? I remember that Chomsky said that there's no underlying structure to language and that for every rule you try to make you'll always find an edge case that contradicts the rule.
Very well explained. This video is must watch for anyone who wants to demystify the latest LLM technology. Wondering if this could be made into a more generic video with a quick high-level intro on neural networks for those who aren't in the field. I bet there are millions out there who want to get a basic understanding of how ChatGPT/Bard/Claude work without an in-depth technical deep dive.
OMG the BEST transformers video EVER!
Excellent explanation i ever seen, recommending everyone's this link
Soo cool! Great work
How did you sync your talking cadence to the background music?
Simplest Explanation ever
Amazing video, thank you so much!
When I was a kid, I knew the trouble of translation were due to literally translation words, without contextual/ sequential awareness. I knew it's important to distinguish between synonyms. I've imagined there's a button that generate the translation output then you can highlights the you words that doesn't make sense or want improvement on it . then regenerate text translation. this type of nlp probably exist before I program my first hello world (+15y ago)!
very well explained.👍
Super Explanation!!
Very well explained. Thank you.
It was funny and instructive. Thanks 🙂
Thank you
When I saw this title, I was hoping to better understand the mathematical workings of transformers such as matrices and the like. Maybe you could do a follow-up video explaining mathematically how transformers work.
thank you for your time
Thanks! Great video.
Great video.
Very informative video. Thank you!
Positional encoding = time, attention = context, self attention = thumbprint (knowledge)... looks like a good start for AGI 😀
great video, thanks!
Thanks! This is a great intro video!
Nicely done. Very helpful. Thanks!
phenomenal video
Very impressive video. Thanks for the way you shared information via this video.
Reference your video timeline 05:05, how you created such a video, please.
You have actually given the BEST explanation on Neural Machine Translation that I read so far but you are missing a few elements
But your explanations, your analyses and your delivery are excellent. You're definitely a great communicator and teacher.
Actually Google and others have an algo they're not interested in sharing and I pretty much know what it is. I am working with my programmer on the coding of my new app, the revolutionary Universal Sentence builder and the Universal Dictionary and I keep adding and changing stuff to simplify the concept and I push at a later date the programming of my Sentence Analyser app. It is like most of my apps a simple (and brilliant concept) coded with very few lines of code.
You know Alfred Hitchcock was always adapting into the screen his scenario never changing anything not even a comma while Francis Ford Copolla (The Godfather) was doing the opposite: They say that his script was like a newspaper that had new contents every day. Well I am more like Copolla with my apps. I change stuff all the time and I usually make my programmers go crazy. It's a good sign. :-) Mind you I don't know if one can do like Hitchcock with an app. Come up with a definite version once and for all. This would be quite an achievement!
In the case of my Universal Sentence builder, the main task was to process the data entered by the user and we've been at it since July 2022. :-) It's either I am dumb or it is a complex task. Actually it is the latter for I have started with French, this langage being the most complex in the world. The good news is I am sure I will be imitated but you can rest assured that my imitators will also have a jolly hard time with French :-)
NICE SUPERB PRESENTATION
From 5:28, shouldn't it be the following:
"when the model outputs the word “économique,” it’s attending heavily to both the input words “European” and “Economic.” "?
For européenne, I see that it is attending only to European. Please let me know if I am missing something here. Thanks for the great video.
Thank you for sharing
this is brilliant
Please remove background music, it's really disturbing when you only listen to this otherwise great video
Pretty nice, is there any automatic way of cleaning up data with errors such as a mislabel, or a grammar error?
Ask chatgpt
woww, she's good at explaining things
Great video. Thx.
10/10. Very helpful
So, question: given the goal of understanding meaning within language regardless of language, could a sophisticated enough set of weights derived from a sufficiently large dataset represent essentially the human genome of language?
Amazing video, thank you ... can you use transformers to detect patterns in random data that which is supposedly unpredictable, like weather or stocks?
the unpredictability of stuff like weather and stocks has to do with the fundamental underlying nature of those phenomena so I would bet no.
Thanks, that was very interesting
I'll jump on where others are doing the same - would love advice for someone who understands half the concepts that are alluded to as complex naturally and the innovation feels obvious I'm unsure how to break into the space without some guidance or connection between having exactly that great natural grasp but wildly anxious that language and logic are strengths and math is a mental turn off. For someone needing that type of translation/guide where my approach is language usage & finer cues what is the key terms to get to that understanding? Hate being fascinated and all the tools to play in this space and being unable to start because how I approach topics so welcome any advice.
Just go to school.
Great content 👍
The invention of transformers seems to have jump-started a revolutionary acceleration in machine learning! Between the models you mentioned here, plus the way transformers are combined with other network architectures in DALL-E 2, OpenAI Jukebox, PaLM, Chinchilla/Flamingo, Gato -- it seems like adding a transformer to any model produces bleeding-edge, state-of-the-art-or-better performance on basically any tasks.
Barring any major architecture innovations in the future, I wonder if transformers end up being the key we need to reach human levels of broad-range performance after all 🤔
@Dino Sauro They're certainly not dead, since they're still being incorporated into the bleeding edge AIs. But technology is always evolving, building upon one idea to create the next. If you're hoping for a "final architecture" that will be the best and never replaced by anything else, you're out of luck.
While I respect Professor Marcus, his ideas about the requirements for AGI strongly imply that intelligent design is required for true intelligence to emerge, and I think evolution contradicts that view.
@Dino Sauro Um... Okay, friend, whatever you say. Have a nice life.
I think you are right...we just saw its use in ChatGPT...and I think ChatGPT is just a glimpse of what future holds and how it will affect the IT, EV and Industrial Automation Industry.
Am I right? You wanna add something to it?
@@tanweeralam1650 I agree. ChatGPT, though, is really just GPT-3 with a larger input layer, and human-guided reinforcement learning on top of it. Which is a step in the right direction for sure, but not as huge a development as a lot of people are touting it to be.
From what I can tell, there are three issues that need to be solved before transformer-based (or transformer-incorporating) AIs can reach truly human levels of intelligent behavior.
(1) They need to be bigger. If we think of the model parameter size as analogous to brain synapses, there are about a quadrillion synapses in a human brain, which is orders of magnitude more than the biggest current transformers. For instance, the largest single transformer model is 207 billion parameters, and the largest transformer-incorporating language model is 1.75 trillion parameters. On the other hand, such models don't need to allocate parameters for things like body maintenance, reproduction, etc., so it's not a 1-to-1 correspondence, but I think it's a good estimate for the order of magnitude we need to reach before we get to human levels of sapience. That said, models keep getting bigger, so I have no doubt we'll achieve this within the next decade at most.
(2) Multimodality is important. A lot of "common sense" understanding that AIs seem to lack can likely be attributed to their lack of variety in types of input they can learn from. If you only learn from text, it's a lot harder to learn what the described concepts actually *mean.* On the other hand, a model that can learn from text, images, video, audio, and other forms of data should be able to learn much more accurate representations of the world. And of course, there's a TON of research into multimodal learning right now, so we'll get there pretty soon, too, I think.
(3) The third obstacle I think is the hardest: continual learning. (From what I can tell, by the way, "continual learning" is synonymous with "incremental online learning". Let me know if there are any important differences between the two.) An AI without this can learn from a *ton* of data, but once it does, it stops learning and everything it knows is set in stone. In effect, this means every interaction with such an AI "resets" it, and so you might get inconsistent behaviors as slightly different initial conditions of an interaction can lead to very different outputs when previous similar interactions are not incorporated into the model's weights (which, in this context, can be thought of as its "long term memory"). This also means the AIs can't form consistent opinions, since any opinion they might espouse in one conversation is immediately forgotten for the next.
Continual learning techniques already exist for smaller networks, but they are not at all efficient enough to practically apply to these very large language models of many billions of parameters or more. Which is a shame, because I'd speculate that larger models would be less prone to retroactive interference -- "catastrophic forgetting" -- than smaller ones, if we could efficiently incrementally train them.
@@IceMetalPunk I did understand your first 2 points and agree with it...but I want to slightly differ with your 3rd point.
I dont understand...Why would the AI would stop learning?? Due to its storage space, Processing power exhaustion or for what reason? What you said may be a POSSIBILITY...But its others side also exists...it may just continue learning more n more and make it's system better.
To have Human like Intelligence...I dont think it will achieve that in next 30-40 yrs...far from those timeline...I can't say. And frankly there is NO NEED to have AIs so Advanced. Upto a certain extent...AIs should develop and Humans MUST BE able to control them. Always.
And can you say will Programs like ChatGPT ( i mean its advanced form) able to replace search Engine like Google in future?? Also how AI/ML will affect IT industry as a whole and also EV, Industrial Automation industry (e.g.- the industry where companies like Siemens, Honeywell operate)??
can anyone help me understand bart model which is used in chat GPT3, and how to train it?
Fantastic video
Thank you so much for your help. With the assistance of GPT-4, I have been able to transition from a seasonal programmer to a full-time programmer. I am truly grateful for your support!
Nice to hear that
Wowww….thanks for clarifying my confusion.