= = I have a feeling that I accelerate the video.....since he speaks so fast
@macevsculture5 жыл бұрын
@@Penaming 1.25 speed is even better
@tacitlytesla79124 жыл бұрын
He just speaks very staccato, I think he speaks normal speed
@grlldfsh1235 жыл бұрын
I love listening to things I cannot understand
@berargumen23904 жыл бұрын
Keep listening, you will eventually understand
@alvinphantomhive37944 жыл бұрын
makes u feel smart uh? cause i felt it that way too 😂
@colinmaharaj3 жыл бұрын
Don't say that, give it time.
@anuraghivare58753 жыл бұрын
Same here.....😂😂🤦♂️
@HemangJoshi2 жыл бұрын
For real bro . For real... 🤣🤣🤣🤣
@rishabhpatra49503 жыл бұрын
Anybody just love the way Karpathy speaks? Makes me want to listen to him with intent
@MohammedYounis-w6h3 жыл бұрын
same, he just gets to the meat of the stuff right away
@colinmaharaj3 жыл бұрын
Interesting you'd say that, there is so much to learn even from asian schools like in India for example, but some accents can be harse when you watch the videos. Whats interesting about what you said is I think Andrew Ng also speaks eloquently and his lectures are worthy of a listen, and its the same topic area.
@endgamefond8 ай бұрын
Agreed. Idk if it is the nervous pause or else but he is so interesting when he explains stuff.
@marciovenanciobatista7 жыл бұрын
Hi from Brazil!! Thank you for sharing this. It is a really good material for researchers and who is initiating in this area.
@PaAGadirajuSanjayVarma4 жыл бұрын
Thank you lex sir for posting this
@gue22128 жыл бұрын
Hey Lex, can´t thank you enough for splitting up the day-long streams! Much easier to consume -- as I wanted to download to enjoy it on mobile! I came across Andrej Karpathy´s Deep Learning for Computer Vision yesterday. I´ve been trying to really understand CNNs and the Deep Learning paradigms technically for some time now and sucked up everything I could since July. Andrej´s lecture is the very best I found to get up to speed on most important details in the least possible time. Cheers G.
@MawaMaverick5 жыл бұрын
Yest i watched it 2 days before i watched this one as well. Andrej Karpathy's lecture is absolutely amazing. He covers so much in such a short time with such detail.
@livesportshub5 жыл бұрын
This People, They did not understand anything but they liked him.
@karanpatel14192 ай бұрын
How did this went under my radar for 7+ years
@sanchitsinghiitg7 жыл бұрын
omg! He has done a great job in explaining this entirely new field of research in an hour!
@TheFireHacker7 жыл бұрын
Great video. I came here after completing 4 video sessions by Lex (MIT 6:S094). Thanks for compling these videos.
@bingeltube6 жыл бұрын
Very recommendable! Good overview!
@russianmadman17 жыл бұрын
This is a great talk, really helped with my university project
@maged_helmy4 жыл бұрын
Does someone have 2016, 2017, 2018, and 2019 winning architectures list?
@gibrains3 жыл бұрын
This why youtube has playback speed settings.
@rui5692 жыл бұрын
🤓
@ridhakiller3 жыл бұрын
Amazing
@gue22128 жыл бұрын
Extra comment, so the important link is visible without expanding: I´m looking forward to dig into the extended version, namely the CS231n Winter 2016 Lecture series referenced in the video. (at kzbin.info/www/bejne/nV6zp4uLn6lpp8k )
@thesezeshacks91635 жыл бұрын
Ok I disagree with how he answered the woman's question. There is a way to choose a MINIMAL amount of layers, based on the complexity of the data. It depends on convexity vs non-convexity in the data space. non-convexity requires a minimum of 2 hidden layers to represent. This is why before you dig into deep learning and all the modern stuff a good basis in Universal Approximation Theory and NN's as Universal Approximators is critical!
@offchan7 жыл бұрын
27:02 How are the gradients computed? 1) Gradients of the loss with respect to the activation 2) Gradients of the mean/sum of activations with respect to the input image
@maosun74747 жыл бұрын
I think it compute the lost in the last layer and do the back propagation to compute the gradient of each layer so as to optimize.
@offchan7 жыл бұрын
That is choice number 1.
@1Kapachow18 жыл бұрын
Great lecture - thanks! :)
@maqboolfida7864 жыл бұрын
The first terminators on the planet would sound exactly like Andrej Karpathy!... love to see him say 'I'll be back' :)
@QuintinMassey4 жыл бұрын
So amazing...
@xDMrGarrison2 жыл бұрын
that deepvis demo was kinda magical and mindblowing..
@aydtsang3 жыл бұрын
does anyone know why lex hasn't had karpathy on the podcast yet?
@MahJohn2 жыл бұрын
I ask myself this question as well. Just wondering!
@Splish_Splash Жыл бұрын
so.. know he had
@ahmadkarim86328 жыл бұрын
can anyone load the slides of this presentation
@dciug7 жыл бұрын
At 1:19:40. Isn't that what Google is trying to do right now?
@disectormusic5 жыл бұрын
he is one of the wingmakers
@al7ay3 жыл бұрын
recommend to watch it on x0.75 ))
@matteo7moh7 жыл бұрын
cs231n
@lemyul5 жыл бұрын
thanks frid
@jiansenxmu7 жыл бұрын
Pro-Tip: 0.75x speed. You're welcome :)
@bayoudhkhaled10347 жыл бұрын
Good explanation
@ae_acar8 жыл бұрын
Cool, thanks
@sournest11 ай бұрын
Cell phone distributed training is a radical idea.🤔🤔🤔