What are GANs (Generative Adversarial Networks)?

Поделиться
HTML-код
  • Опубликовано: 26 ноя 2024

Комментарии • 207

  • @baqirhussein1109
    @baqirhussein1109 2 года назад +66

    I like the way he smiles and the calm talking

  • @canaldot.5243
    @canaldot.5243 7 месяцев назад +15

    Wow, this is the first time I really understand the concept of GAN. Well explained. Loved it

  • @julesnzietchueng6671
    @julesnzietchueng6671 3 года назад +35

    He clearly loves his job and its communicative ^^

  • @skycellinium
    @skycellinium 3 месяца назад +2

    I've just listened, and now I believe I have a solid grasp on how GANs work. I'm confident that this knowledge will stay with me for a long time.

  • @ahmedaj2000
    @ahmedaj2000 Год назад +21

    loved it. simple enough to be understood yet complex enough to get the important details

  • @shubha07m
    @shubha07m Год назад +7

    Just one sentence: The easiest yet more powerful explanation of GAN!

  • @xmlviking
    @xmlviking 11 месяцев назад +2

    I absolutely love this topic. The advances in human medicine could be incredible with this. A sample "input" from a bio organism...and then a model "of you're target cell types"...and then prediction on outcomes...and then further samples of "feedback agent" and then training you're human cell model. Then we introduce the GAN and think about our models accuracy. The future state possibilities of identifying interactions "trainings" with various drugs etc. This type of interaction could lead to identifying bio organisms not just humans and potential outcomes of interactions with them. Extrapolate that with humans and food allergies, diseases etc. It's mind boggling. When he is talking about CNN's and the use of alternate examples with Discriminators and Generators with Encryption my mind exploded. You could, hypothesize a Hedy Lamar like frequency agility but apply that to encryption and use an encryption agile chain. Good lord, super computationally expensive but man that would be nearly unusable from theft point of view. Would take you forever to crack that..as all the data could change from one form to another over time of transmission.

    • @TWHICH
      @TWHICH 10 месяцев назад

      damn

  • @TheAkdzyn
    @TheAkdzyn 7 месяцев назад

    This was excellent. Came across gans a while back but some of the explanations i got were deeply technically complicated so I couldn't quite understand them properly but this was very precise yet relatively concise for the amount of information it conveyed. Well done. I'll look for more from you!

  • @jayanthmankavil
    @jayanthmankavil 11 месяцев назад +3

    Thank you, IBM, for these videos!!

  • @vrundraval6878
    @vrundraval6878 Год назад +4

    this is what you call a clear explanation, thanks

  • @aryamahima3
    @aryamahima3 2 года назад +7

    Just loved his attitude and way of explaining the concepts.. 😊😊😊

  • @deyon4521
    @deyon4521 2 года назад +42

    How is he writing with his left hand, from right to left and mirrored so that i can understand.🧐 Or is this just his secret talent.

    • @IBMTechnology
      @IBMTechnology  2 года назад +12

      If you want to find out we shared some backstage "secrets" on our Community page, you can check it out here 👉 ibm.co/3pT41d5

    • @toenytv7946
      @toenytv7946 2 года назад +1

      Elementary my dear Deyon nice one.

    • @sc1ss0r1ng
      @sc1ss0r1ng 2 года назад +17

      He's writing it normally in front of himself and then they have mirrored the video, so we see what he actually saw when they made the video.

    • @TheSouthernSiren
      @TheSouthernSiren Год назад

      😆

    • @recursosmusicales399
      @recursosmusicales399 Год назад

      Is a fake 😱🤣

  • @nokostunes
    @nokostunes 2 года назад +5

    kudos for the clear explanation + writing all those diagrams backwards :]

  • @huynhphanngockhang5733
    @huynhphanngockhang5733 9 месяцев назад +1

    oh i like his voice so much, he teach very very easy to aproach

  • @kitrt
    @kitrt 3 года назад +10

    How far are we from networks that generate networks, I wonder.
    Like a network that tries to produce the most efficient neural network structure to achieve a good enough result in the shortest amount of time (or cloud resources) in a given use case. Or it's more efficient to just use genetic algorithms?

  • @AishaKyes
    @AishaKyes 2 года назад +11

    this was so easy to understand and interesting, thank you!

  • @robertdTO
    @robertdTO 7 месяцев назад

    Excellent, clear, to the point in introducing GAN.

  • @MOHAMEDNAFILASHIFM
    @MOHAMEDNAFILASHIFM 2 месяца назад

    complex concepts aren't really complex. its all about the teacher, and bro proves it 😎

  • @gurukiranhr
    @gurukiranhr 17 дней назад

    Very well explained with simple language!

  • @aryanarya72
    @aryanarya72 9 месяцев назад

    I loved the way he said in the end - "turn a young, impressionable, and unchanged generator to a master of forgery".🦊🦊

  • @gauravpoudel7288
    @gauravpoudel7288 10 месяцев назад +1

    Appreciate the effort put into generating such great content.
    BTW I don't quite understand how generator and discriminator concept can be applied to :
    predicting the next video frame OR
    creating higher resolution image
    These were discussed in the video at 07:15

    • @parteeks9012
      @parteeks9012 6 месяцев назад

      It can be used as a discriminator. As we can feed some part of the video and ask him what the person is going to do next? if the prediction is correct then feed more hard questions otherwise discriminator has to improve its weight.

  • @GigaMarou
    @GigaMarou 2 года назад +3

    well explained sir! but i don't get the application of GANs in the context of video.

  • @iverjohansolheim5172
    @iverjohansolheim5172 5 месяцев назад

    Very pedagogical setup, loved it!

  • @tanezcorvideos
    @tanezcorvideos Год назад +1

    Really perfect explanation of GAN, well done!!

  • @KW-md1bq
    @KW-md1bq 2 года назад +9

    I don't think it's very nice to talk about someone else's amazing invention without mentioning their name. (Ian Goodfellow created GANs in 2014)

    • @fabianr9394
      @fabianr9394 5 месяцев назад +1

      Well and you're not doing it better. In today's research, there are many "inventors" so saying he invented it himself is not justified. Just look at the original paper and you'll see countless researchers who worked on it to some extent. The concepts are what matters.

  • @lethane11
    @lethane11 2 года назад +2

    Superbly explained. Thank you

  • @usamazahid1
    @usamazahid1 2 года назад +2

    elegant explanation .....great job

  • @sathirawijeratne7872
    @sathirawijeratne7872 10 месяцев назад +1

    Love this explanation!

  • @Surya25398
    @Surya25398 2 года назад +2

    It is really helpful, thanks for your video

  • @elizacampillo7494
    @elizacampillo7494 17 дней назад

    Can you tell me please 🙏 the name of the tool you use to write as a board? it looks amazing.

  • @AixinJiangIvy
    @AixinJiangIvy 10 месяцев назад

    It‘s helpful. Finally know what GANs are, appreciate it.

  • @Democracy_Manifest
    @Democracy_Manifest Год назад +1

    Great video, perfect presentation. Was this artificially generated?

  • @saharghassabi
    @saharghassabi 7 месяцев назад

    Thank you very much... It was so intresting way of teaching this network

  • @MasoodOfficial
    @MasoodOfficial 2 года назад +2

    Excellent Explanation!

  • @yasithudawatte8924
    @yasithudawatte8924 2 года назад +2

    Very well explained😇, thank you.

  • @monicamateu3750
    @monicamateu3750 Месяц назад

    The information given to the Discriminator is in picture format? Is the discriminator admiting for example true premises like 'roses can be any color', or things like that, that probably is not easy to explain by picture..?

  • @Aimeecroft
    @Aimeecroft 9 месяцев назад

    I dont know if your still responding to comments, but ill give it a try!. Im currently looking at deepfakes for undergraduate project. With the GANs updating everytime they lose does this refer to the deeplearning?

  • @engin-hearing5978
    @engin-hearing5978 3 года назад +13

    Very nice video and super clear explanation. I would like to ask a question, staying on the architecture of GANs, one could believe that their results would periodically improve. If this is a possibility, are we measuring how much deep fakes improved from one year (for instance) to another? I think would be interesting to know it to understand if one day we will still be able to detect them through digital forensics algorithms.

    • @Arne_Boeses
      @Arne_Boeses 2 года назад +4

      With better and better Deepfakes generated, also the tech to detect deepfakes gets better and better.

    • @reggaemarley4617
      @reggaemarley4617 2 года назад +1

      @@Arne_Boeses But will detection technology ever be able to outpace generation technology? Based on this video is sounds like discriminator type systems are destined to lose.

  • @blumehao
    @blumehao 2 года назад +1

    you use right hand?

  • @fundatamdogan
    @fundatamdogan 2 года назад +1

    I loved the lesson.But GANs more :)

  • @sapnilpatel1645
    @sapnilpatel1645 Год назад

    Very Informative video.Thanks for making it.

  • @Has_Le_India13
    @Has_Le_India13 Год назад

    if we are giving the discriminator a domain for learning shapes of flower isnt is supervised learning how it is unsupervised since we are providing a domain to learn

  • @andyjc9558
    @andyjc9558 2 года назад +1

    Can I use GANs to generate a lot of Fake defects images of a product and use to train a 1st model?

  • @BintAlAbla1999
    @BintAlAbla1999 2 года назад +3

    Great video, very well done, thank you. I can see it can generate amazing imagery etc.. Allow me to ask a dumb question. What is the point of GANS? How does it enhance learning, for example? I just don't get 'the point'.

    • @Behdad47
      @Behdad47 2 года назад

      Have you found your answer yet?

  • @somuchtech9864
    @somuchtech9864 Год назад

    Very well explained. Thanks for sharing

  • @syedmuhammadsameer8299
    @syedmuhammadsameer8299 Год назад

    For the image upscale problem, would we still feed the generator random noise or will we give it the lower res image?

  • @JohannesNürnberg-c8z
    @JohannesNürnberg-c8z 9 месяцев назад

    Hey there, I am writing my bachelor thesis about how safe facial recognition authenticators will be with improving AI image creation. Would you say that GANs can oppose a risk to facial recognition authenticators?
    Thank you

  • @deonorina
    @deonorina 21 день назад

    i love this guy

  • @jasonchen7758
    @jasonchen7758 2 года назад +2

    He is either a lefty that can write mirror image sentences from right to left in real time, or the video was post processed?

  • @apdy1095
    @apdy1095 2 года назад +1

    can someone tell me wht the core idea behind DDQN and GAN is same

  • @petchpaitoon
    @petchpaitoon 3 года назад +3

    Thank you, It is informative

  • @mhmoudkhadija3839
    @mhmoudkhadija3839 Год назад

    Very nice explanation! Thanks sir

  • @animanaut
    @animanaut Год назад

    what is the difference between a discriminator and a classifier? or are these synonyms. reason i am asking is: classifiers are sometimes mentioned when it comes to detection of generated content. but, if a discriminator in the endstages of many iterations is basically no better than guessing it does not seem a viable solution for this problem

  • @DilawarShah-g9f
    @DilawarShah-g9f Год назад

    I want to generate images through GAN from MIAS dataset. Which GAN architecture is most suitable?

  • @taqiadenal-shameri3800
    @taqiadenal-shameri3800 Год назад

    Amazing explanation

  • @Callmejz.ai01
    @Callmejz.ai01 Год назад

    if this is unsupervised, how does the discriminator "know better be able to tell where we have a fake sample coming in"?
    thank you for your theory, and the flower example! #creatoreconomy

  • @asteralebel2856
    @asteralebel2856 28 дней назад

    what is BigGan and Stylegan?

  • @johnspivack
    @johnspivack 7 месяцев назад

    Good explanations. Thanks.

  • @mddildarmandal9241
    @mddildarmandal9241 4 месяца назад

    Interesting , learnt something new

  • @usama57926
    @usama57926 2 года назад +1

    good explanation

  • @storytimewithme2
    @storytimewithme2 Год назад

    why don't you have a link to the CNN video that he mentions?

  • @sitrakaforler8696
    @sitrakaforler8696 Год назад

    Dam.... thanks for sharing it so clearly !!!

  • @Krunkbitmos
    @Krunkbitmos 8 месяцев назад

    the discrimator is trained a normal way with real flower pictures? how is the generator trained to make the first flower? like how does it know to output certain data in certain size and colors etc? i understand how it can update if wrong but how is the generator actually generating?

    • @quonxinquonyi8570
      @quonxinquonyi8570 Месяц назад

      If you would know it then you will come with your own improved version of Claude,lllma and dall-es….so it’s a trade secret…..the mystery lies in back propagation of loss function from discriminator to generator….coz the overall cross entropy loss function will never ever be useful to train the generator…so it’s not all “adversarial” learning there is some part of “ cooperative learning “ in it which helps generator learn….HOW???? ….that’s billion dollar trade secret

  • @Zackemcee1
    @Zackemcee1 Год назад

    Is this what Nvidia is using for its new frame generation technique in the RTX 40 series? I'm just guessing before checking the internet

  • @alaad1009
    @alaad1009 Год назад

    Excellent video

  • @yuvrajanand1991
    @yuvrajanand1991 Год назад

    Simply Loved it

  • @Evokus
    @Evokus 2 года назад

    Are we just going to ignore the fact that he's writing backwards??? That thing is skill man

    • @uday3350
      @uday3350 Год назад +1

      Relax, he would have flipped the video left to right so that you don't see the text backwards.

    • @tudorrad5933
      @tudorrad5933 Год назад

      I literally spent the entire video not listening to him and asking myself what wizardry he uses to write mirrored.

    • @Billy-sm3uu
      @Billy-sm3uu Год назад +1

      he wrote with his right hand then mirrored the video

  • @basedmatt
    @basedmatt Год назад

    Could somebody explain to me the difference between a GAN and Zero-Shot Learning?

  • @uurv
    @uurv 2 года назад +1

    is this possible to make a one image into different poses, variations. Can anyone reply to this image

    • @hassanbinali1999
      @hassanbinali1999 2 года назад +1

      Yes udaya it is possible. We call this method "data augmentation". You can find a lot of techniques on internet related to this.

  • @keshavmiglani2697
    @keshavmiglani2697 Год назад

    Did DALL-E 2 use GAN?

  • @myentropyishigh8708
    @myentropyishigh8708 4 месяца назад

    thank you sir!.

  • @subodhi6
    @subodhi6 2 года назад +2

    Thank you..!

  • @croom0101
    @croom0101 17 дней назад

    Is it necessary that the discriminator should be trained first ?, As the training is independent on each other, why can't we train the generator first?

  • @minjun9900
    @minjun9900 4 месяца назад

    was really helpful

  • @abdurrouf4159
    @abdurrouf4159 10 месяцев назад

    Well explained.

  • @EmpoweredWithZarathos2314
    @EmpoweredWithZarathos2314 Год назад

    Loved it😅

  • @heidikeller50
    @heidikeller50 Год назад

    Super- thank you :)

  • @leif1075
    @leif1075 Год назад

    Didn't most everyone else think that is not what zeromsum game meant..inthoight if there is an advantage for one player that would not be a zero sum game..

  • @debayanguha3026
    @debayanguha3026 2 года назад +1

    thank you ,it's great ...!

  • @saifshaikh8679
    @saifshaikh8679 6 месяцев назад

    Are Generators used for creating deep fakes?

  • @RuiMartins
    @RuiMartins 2 года назад +1

    I hope the host understands that he could write normally, instead of reflected, since he just needs to mirror the video in the end and everything would be correct from the viewers view.

  • @fastrobreetus
    @fastrobreetus 2 месяца назад

    TY

  • @MdAbdullah-gn6uj
    @MdAbdullah-gn6uj 7 месяцев назад

    Nice video

  • @java2379
    @java2379 Год назад

    I don't get that the discriminator should be updated if the generator succeeds. The image was 'fake' ( i would say synthesized ) and the whole point of the game beeing to teach the generator how to synthesize image that are as far as possible close to the 'real data' dataset. There is no failure per say.
    It all depends on what you means by fake:
    1- Fake means even if its a realistic flower but does not belong to the 'real' dataset it a fake.
    2- Fake means its not a flower ,its a car , or garbage so the discriminator is unhappy of the generator's job.
    You seem to define fake as per definition 1 ; in this case , you can directly compare image pixels by pixels and calculate euclidian distance for the error to backpropagate on the generator, you don't need a neural network for the discriminator , do you?
    So i think the correct definition is 2. Hence the discriminator never has to learn from the generator.
    >> I know you work for IBM , so its likely that i missed a point , kindly let met know 🙂

  • @sharongreenlaw8096
    @sharongreenlaw8096 22 дня назад

    Have we started mining yet?

  • @DavOlek_ua
    @DavOlek_ua 3 года назад +2

    picture is mirrored? my brain is glitching and I don't know why lol

    • @IBMTechnology
      @IBMTechnology  2 года назад +1

      Hey there! We shared some behind the scenes of our videos on the Community page, check it out here 👉 ibm.co/3dLyfaN 😉

    • @DavOlek_ua
      @DavOlek_ua 2 года назад +1

      @@IBMTechnology haha I knew it is exactly like that!)

  • @golamrob
    @golamrob 6 месяцев назад

    excellent

  • @whatnext767
    @whatnext767 3 месяца назад

    The video is mirrored.
    I think because he is actually writing the text for his view (offcourse), but to us it would show mirrored, so to correct this, the whole video is mirrored again. and the watch is an additional proof

  • @--Dipanshu--
    @--Dipanshu-- 10 месяцев назад

    how is he writing backwards?

    • @aryanarya72
      @aryanarya72 9 месяцев назад

      He's not writing backwards. It appears as if he is. He is writing normally like you would on a board or a notebook.

  • @sharongreenlaw8096
    @sharongreenlaw8096 22 дня назад

    So we certainly have a glitch or trojen horse in the world's GAN don't we?

  • @prateekkatiyar9532
    @prateekkatiyar9532 3 года назад +2

    Great

  • @erikschiegg68
    @erikschiegg68 2 года назад +1

    Gimme Ampere 100 Now! (GAN)
    Just for StyleGAN3, please, sir.

    • @sc1ss0r1ng
      @sc1ss0r1ng 2 года назад

      no, you give me 100 amperes now and also 1500 volt, madam. I will not ask twice, hand it over, or you will be shocked, by the consequences.

  • @IshanJawade
    @IshanJawade 6 месяцев назад

    How can he write upside down

  • @techwithbube
    @techwithbube 3 года назад +3

    First to comment .

  • @drakefruit
    @drakefruit 2 года назад +2

    how do you write backwards so well lol

  • @THEMATT222
    @THEMATT222 2 года назад +1

    Noice 👍 Doice 👍 Ice 👍

  • @NorrisKingsley-m5y
    @NorrisKingsley-m5y 2 месяца назад

    Wilkinson Trail

  • @VelvetWraith-i3z
    @VelvetWraith-i3z Месяц назад

    great

  • @MdAbdullah-gn6uj
    @MdAbdullah-gn6uj 7 месяцев назад

    Nice

  • @DanMeroy-s2m
    @DanMeroy-s2m 2 месяца назад

    Irwin Plains