Тёмный
Pi School
Pi School
Pi School
Подписаться
A next-generation kind of school where Machine Intelligence meets Human Creativity. For game changers, entrepreneurs, risk takers building an amazing future.
Graph Theory for Orchestrating LLM Workflows
51:31
3 месяца назад
Pitch Day Pi School of AI Session 14
51:43
8 месяцев назад
AI Travel Assistant: a case study of La Filanda
6:31
11 месяцев назад
Комментарии
@ytubeanon
@ytubeanon 2 месяца назад
is this guy one of the father's of modern AI? is he a primary reason for chatGPT?
@mathforai-j5y
@mathforai-j5y Месяц назад
yes
@yusufcan1304
@yusufcan1304 4 месяца назад
thanks.
@Cropinky
@Cropinky 5 месяцев назад
very interesting of him to call deep learning a trade :)
@ShadowD2C
@ShadowD2C 6 месяцев назад
good video but his and the camera placements are subobtimal
@ds920
@ds920 8 месяцев назад
I’m based in Milan, any chances any events will take place in Milan as well? I working on computational environment for agents. Already in production to some degree.
@vashisthegde2169
@vashisthegde2169 Год назад
Great work guys! ❤🎉🎉
@CharlesVanNoland
@CharlesVanNoland Год назад
I just wish he hadn't stood right in front of what he was trying to show people, but I love his passion for explaining what he's talking about.
@alexandrogomez5493
@alexandrogomez5493 Год назад
Tarea 6
@ARE_YOU_SICK_OF_YT_CENSORSHIP
i notice that Yasmin Moslem is the only person without a photo, is being photographed for public display against her religious beliefs, does she also not appear in public in person, or is she simply a virtual mentor who doesn't exist in the real world?
@pischool6210
@pischool6210 Год назад
She is a human, a researcher, but she does not want to appear. We understand it might be strange for a human in 2023, but we respect and support any choices.
@ARE_YOU_SICK_OF_YT_CENSORSHIP
what these systems don't do i suppose is recognize text from images/scans which translators work a lot with so accurate text extraction from source is often required before the actual translation could be performed unless this software is able to not only extract text but also correct all the errors which are usually associated with OCR, and the more exotic the writing system the more challenging is the extraction task
@pischool6210
@pischool6210 Год назад
These aren't multimodal models as they were trained only on text data (specifically for Machine Translation), so they can't be used to extract text from images. What you're probably looking for are models trained for Document Understanding tasks, such as the one we covered last session of School of AI (ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-gXSFE0TznGM.html&ab_channel=PiSchool)
@ARE_YOU_SICK_OF_YT_CENSORSHIP
@@pischool6210 thank you for the link, i'll take a look
@someone_518
@someone_518 Год назад
ChatGPT gave me link to this video)
@IExSet
@IExSet Год назад
Strange thing, he mention "attention" term before explaining what it is. What was EXACT meaning of this Query Key Value magic ??? I suspect speakers just copy thoughts of another people mechanically, not understaning real meaning of operations !
@ahmedb2559
@ahmedb2559 Год назад
Thank you !
@ShahNawaz-zb3bu
@ShahNawaz-zb3bu 2 года назад
Great describon. Love from Pakistan 🇵🇰
@nabinchaudhary73
@nabinchaudhary73 2 года назад
does embedding gets trained or key or query or value gets trained i am confused. please help
@kingenking9303
@kingenking9303 2 года назад
the video image is too poor, you need to fix it more
@tenzinkaldan2007
@tenzinkaldan2007 3 года назад
where can i find the implementation
@uhmerikuhn
@uhmerikuhn 3 года назад
...comes from Google - Check. ...TensorFlow T-shirt - Check. Most viewers therefore rate this lecture highly - Check. This is very hand-wavy throughout with relatively no rigor shown. There are many lectures/presentations online which actually explain the nuts and bolts and wider use cases of Attention mechanisms. Maybe the title of this video should be something else, like "Our group's success with one use case (language translation) of Attention." Frankly, the drive-by treatment of the technical details of language translation case was almost terrible and should have probably been omitted.
@georgemaratos1122
@georgemaratos1122 3 года назад
which lectures do you like that explain attention mechanisms and their wider use?
@natalescarpato9411
@natalescarpato9411 3 года назад
Tokio
@adrianradu1298
@adrianradu1298 3 года назад
7y30 8
@marioerrante6717
@marioerrante6717 3 года назад
Gg v cejtqnhmmt i io
@louerleseigneur4532
@louerleseigneur4532 3 года назад
Thanks buddy
@robertc6343
@robertc6343 3 года назад
Fantastic talk!
@tylersnard
@tylersnard 3 года назад
I love how excited he is.
@brandomiranda6703
@brandomiranda6703 3 года назад
where is the library he talks about to get the details of training the DL "right"?
@kvsnoufal
@kvsnoufal 3 года назад
31:55
@brandomiranda6703
@brandomiranda6703 3 года назад
@@kvsnoufal is there one for pytorch?
@lmaes
@lmaes 3 года назад
The passion that he transmits is priceless
@kadamparikh8421
@kadamparikh8421 3 года назад
Great content in this video. Would love if you had the multi-headed devil covered! Though, great video to get the overall view..
@empowercode
@empowercode 3 года назад
Hey! I just found your channel and subscribed, love what you're doing! I appreciate how clear and detailed your explanations are as well as the depth of knowledge you have surrounding the topic! Since I run a tech education channel as well, I love to see fellow Content Creators sharing, educating, and inspiring a large global audience. I wish you the best of luck on your RU-vid Journey, can't wait to see you succeed! Your content really stands out and you've put so much thought into your videos! Cheers, happy holidays, and keep up the great work!
@harryderek521
@harryderek521 3 года назад
Very nice 😍💋 💝💖♥️❤️
@fisherroberto3570
@fisherroberto3570 3 года назад
Love you 💋💋😘😘❤️💯
@jahanzaibanwar5946
@jahanzaibanwar5946 3 года назад
Hi nice project. If that’s okay can you share the GitHub link?
@clray123
@clray123 3 года назад
Most I gather from this talk is that "attention" is a pretty terrible term. Something like "fuzzy lookup" or "matching" or "mapping" would have been much more descriptive, but oh well, which researcher needs to think about terminology before unleashing it on the world.
@sajjadayobi688
@sajjadayobi688 3 года назад
Transformers learned translation without language dependency O_o
@RobertElliotPahel-Short
@RobertElliotPahel-Short 4 года назад
math majors/ graduate math students skip to 15:36
@sudiplingthep7409
@sudiplingthep7409 4 года назад
in two months i am starting a farm here in nepal, looks useful for me aswell how can i know more about smartcrop.
@vast634
@vast634 4 года назад
They should invent a device that can always tell the time of day when the user wants.
@TheAIEpiphany
@TheAIEpiphany 4 года назад
47:55 "We tried it on images it didn't work so well". 2020, Visual Transformer: am I a joke to you?
@souhamghosh8714
@souhamghosh8714 4 года назад
In VIT, it is clearly stated that a "small dataset" like imagenet doesnt show promising results but a larger dataset like the jft gives amazing results, so this maybe a start, but it is far from perfection. Btw, I am not contradicting your statement. 😁. and also JFT is not an open source dataset(yet)
@TheAIEpiphany
@TheAIEpiphany 4 года назад
@@souhamghosh8714 True Google folks ^^
@souhamghosh8714
@souhamghosh8714 4 года назад
“Hi, I am from google, you know what i got, TPUs..more than you can imagine”😂
@AlexVoxel
@AlexVoxel 4 года назад
Interessante, grazie
@pankajtiwari12
@pankajtiwari12 4 года назад
great explanation !
@pankajtiwari12
@pankajtiwari12 4 года назад
@27:14 multitasking
@autripat
@autripat 4 года назад
Starting @ 15:45, in well under 2 minutes, attention explained! Only a true master can do it. Love.
@Scranny
@Scranny 4 года назад
K is a matrix representing the T previously seen words and V is the matrix representing the full dictionary of words of the target language, right? But what are K and V exactly? What values do these matrices hold? Are they learned?
@FranckDernoncourt
@FranckDernoncourt 4 года назад
Thanks for sharing! It'd be great if the video could pay more attention to the slides though.
@pischool6210
@pischool6210 4 года назад
Thank you for your comment, Franck! You can download the slides here: picampus-school.com/open-day-2017-presentations-download/
@FranckDernoncourt
@FranckDernoncourt 4 года назад
@@pischool6210 perfect, thanks!
@HimanshuGhadigaonkar
@HimanshuGhadigaonkar 4 года назад
Best expaination!!
@Marcos10PT
@Marcos10PT 4 года назад
This is the best explanation of attention I have seen so far! And I have been looking :)
@ksrajavel
@ksrajavel Год назад
Bcoz, he is one of the co-author of the revolutionary paper which introduced it
@jayantpriyadarshi9266
@jayantpriyadarshi9266 4 года назад
Great talk. Something very useful.
@ramyaneekashyap4356
@ramyaneekashyap4356 4 года назад
Is there any way i could get the ppts for reference?
@pischool6210
@pischool6210 4 года назад
Hi, sure! You can download it here: picampus-school.com/open-day-2017-presentations-download/
@ramyaneekashyap4356
@ramyaneekashyap4356 4 года назад
@@pischool6210 thankyou so much!!!!
@kunalaneja1720
@kunalaneja1720 4 года назад
Hey can you please send the model to me for this project
@taimoor722
@taimoor722 4 года назад
nice
@GeorgeZoto
@GeorgeZoto 4 года назад
Great session Pi School 📚and Łukasz 😀. Here are a few key concepts I "attended" to and found interesting: "There is always another head that whatever word it is in, it looks at the (head) noun of the sentence or the (head) verb, just wants to know what are we talking about here 🤔" - Łukasz Kaiser ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-rBCqOTEfxvg.html "n^2 * d seems worse than n * d^2 (on attention vs recurrent algorithmic/operation complexity). Luckily at Google there is guy name Noam (Shazeer), he never got his bachelor but wrote most of these papers..." - Łukasz Kaiser ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-rBCqOTEfxvg.html "We trained a model to translate from English to French and vice versa, and from English to German and vice versa. Then if you give it French and ask for a German translation it will do a reasonable job. Multitask helps with deep learning tasks where you have little data." - Łukasz Kaiser ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-rBCqOTEfxvg.html
@shashidhar775
@shashidhar775 4 года назад
Can i see the code?
@skinnyboy996
@skinnyboy996 4 года назад
Your book on Go is the best