Deep Learning for Computer Vision (Andrej Karpathy, OpenAI)

แชร์
ฝัง
  • เผยแพร่เมื่อ 12 พ.ย. 2024

ความคิดเห็น • 59

  • @rishabhpatra4950
    @rishabhpatra4950 4 ปีที่แล้ว +7

    Anybody just love the way Karpathy speaks? Makes me want to listen to him with intent

    • @HandheldGamingHQ
      @HandheldGamingHQ 3 ปีที่แล้ว +1

      same, he just gets to the meat of the stuff right away

    • @colinmaharaj
      @colinmaharaj 3 ปีที่แล้ว

      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.

    • @endgamefond
      @endgamefond 9 หลายเดือนก่อน

      Agreed. Idk if it is the nervous pause or else but he is so interesting when he explains stuff.

  • @sanchitsinghiitg
    @sanchitsinghiitg 7 ปีที่แล้ว +16

    omg! He has done a great job in explaining this entirely new field of research in an hour!

  • @gue2212
    @gue2212 8 ปีที่แล้ว +11

    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.

    • @MawaMaverick
      @MawaMaverick 5 ปีที่แล้ว +1

      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.

  • @karanpatel1419
    @karanpatel1419 3 หลายเดือนก่อน +1

    How did this went under my radar for 7+ years

  • @marciovenanciobatista
    @marciovenanciobatista 7 ปีที่แล้ว +7

    Hi from Brazil!! Thank you for sharing this. It is a really good material for researchers and who is initiating in this area.

  • @TheFireHacker
    @TheFireHacker 7 ปีที่แล้ว +2

    Great video. I came here after completing 4 video sessions by Lex (MIT 6:S094). Thanks for compling these videos.

  • @grlldfsh123
    @grlldfsh123 5 ปีที่แล้ว +52

    I love listening to things I cannot understand

    • @berargumen2390
      @berargumen2390 4 ปีที่แล้ว +4

      Keep listening, you will eventually understand

    • @alvinphantomhive3794
      @alvinphantomhive3794 4 ปีที่แล้ว

      makes u feel smart uh? cause i felt it that way too 😂

    • @colinmaharaj
      @colinmaharaj 3 ปีที่แล้ว

      Don't say that, give it time.

    • @anuraghivare5875
      @anuraghivare5875 3 ปีที่แล้ว +1

      Same here.....😂😂🤦‍♂️

    • @HemangJoshi
      @HemangJoshi 2 ปีที่แล้ว

      For real bro . For real... 🤣🤣🤣🤣

  • @xDMrGarrison
    @xDMrGarrison 2 ปีที่แล้ว

    that deepvis demo was kinda magical and mindblowing..

  • @russianmadman1
    @russianmadman1 7 ปีที่แล้ว +4

    This is a great talk, really helped with my university project

  • @maqboolfida786
    @maqboolfida786 4 ปีที่แล้ว

    The first terminators on the planet would sound exactly like Andrej Karpathy!... love to see him say 'I'll be back' :)

  • @incendioraven4269
    @incendioraven4269 7 ปีที่แล้ว +42

    = = I have a feeling that I accelerate the video.....since he speaks so fast

    • @macevsculture
      @macevsculture 5 ปีที่แล้ว

      @@Penaming 1.25 speed is even better

    • @tacitlytesla7912
      @tacitlytesla7912 5 ปีที่แล้ว

      He just speaks very staccato, I think he speaks normal speed

  • @PaAGadirajuSanjayVarma
    @PaAGadirajuSanjayVarma 4 ปีที่แล้ว +1

    Thank you lex sir for posting this

  • @offchan
    @offchan 7 ปีที่แล้ว +1

    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

    • @maosun7474
      @maosun7474 7 ปีที่แล้ว

      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.

    • @offchan
      @offchan 7 ปีที่แล้ว +1

      That is choice number 1.

  • @livesportshub
    @livesportshub 5 ปีที่แล้ว +1

    This People, They did not understand anything but they liked him.

  • @QuintinMassey
    @QuintinMassey 4 ปีที่แล้ว +1

    So amazing...

  • @1Kapachow1
    @1Kapachow1 8 ปีที่แล้ว +4

    Great lecture - thanks! :)

  • @bingeltube
    @bingeltube 6 ปีที่แล้ว

    Very recommendable! Good overview!

  • @ridhakiller
    @ridhakiller 3 ปีที่แล้ว +1

    Amazing

  • @bayoudhkhaled1034
    @bayoudhkhaled1034 8 ปีที่แล้ว

    Good explanation

  • @jiachenglee2554
    @jiachenglee2554 7 ปีที่แล้ว +10

    slides: docs.google.com/presentation/d/1Q1CmVVnjVJM_9CDk3B8Y6MWCavZOtiKmOLQ0XB7s9Vg/edit#slide=id.p

  • @jiansenxmu
    @jiansenxmu 7 ปีที่แล้ว +5

    Pro-Tip: 0.75x speed. You're welcome :)

  • @disectormusic
    @disectormusic 5 ปีที่แล้ว

    he is one of the wingmakers

  • @thesezeshacks9163
    @thesezeshacks9163 6 ปีที่แล้ว

    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!

  • @pkr619
    @pkr619 4 ปีที่แล้ว +1

    the fun starts @28:14

  • @gibrains
    @gibrains 3 ปีที่แล้ว +1

    This why youtube has playback speed settings.

    • @rui569
      @rui569 2 ปีที่แล้ว

      🤓

  • @lemyul
    @lemyul 5 ปีที่แล้ว

    thanks frid

  • @aydtsang
    @aydtsang 4 ปีที่แล้ว +1

    does anyone know why lex hasn't had karpathy on the podcast yet?

    • @MahJohn
      @MahJohn 2 ปีที่แล้ว

      I ask myself this question as well. Just wondering!

    • @Splish_Splash
      @Splish_Splash ปีที่แล้ว

      so.. know he had

  • @maged_helmy
    @maged_helmy 4 ปีที่แล้ว

    Does someone have 2016, 2017, 2018, and 2019 winning architectures list?

  • @al7ay
    @al7ay 3 ปีที่แล้ว

    recommend to watch it on x0.75 ))

  • @ahmadkarim8632
    @ahmadkarim8632 8 ปีที่แล้ว +1

    can anyone load the slides of this presentation

  • @ae_acar
    @ae_acar 8 ปีที่แล้ว

    Cool, thanks

  • @sournest
    @sournest ปีที่แล้ว

    Cell phone distributed training is a radical idea.🤔🤔🤔

  • @pratik245
    @pratik245 2 ปีที่แล้ว

    Great

  • @gue2212
    @gue2212 8 ปีที่แล้ว

    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 th-cam.com/video/g-PvXUjD6qg/w-d-xo.html )

  • @dciug
    @dciug 7 ปีที่แล้ว

    At 1:19:40. Isn't that what Google is trying to do right now?

  • @matteo7moh
    @matteo7moh 7 ปีที่แล้ว +7

    cs231n

  • @aaaa8766
    @aaaa8766 4 ปีที่แล้ว

    slides

  • @alexanderskusnov5119
    @alexanderskusnov5119 ปีที่แล้ว

    Low resolution.

  • @kodamusic3327
    @kodamusic3327 ปีที่แล้ว

    даня кода