What are GANs (Generative Adversarial Networks)?

Поділитися
Вставка
  • Опубліковано 29 лис 2024

КОМЕНТАРІ • 207

  • @baqirhussein1109
    @baqirhussein1109 2 роки тому +67

    I like the way he smiles and the calm talking

  • @canaldot.5243
    @canaldot.5243 7 місяців тому +15

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

  • @julesnzietchueng6671
    @julesnzietchueng6671 3 роки тому +35

    He clearly loves his job and its communicative ^^

  • @ahmedaj2000
    @ahmedaj2000 Рік тому +21

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

  • @skycellinium
    @skycellinium 4 місяці тому +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.

  • @shubha07m
    @shubha07m Рік тому +7

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

  • @xmlviking
    @xmlviking Рік тому +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 місяців тому

      damn

  • @TheAkdzyn
    @TheAkdzyn 7 місяців тому

    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!

  • @vrundraval6878
    @vrundraval6878 Рік тому +4

    this is what you call a clear explanation, thanks

  • @aryamahima3
    @aryamahima3 2 роки тому +7

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

  • @jayanthmankavil
    @jayanthmankavil 11 місяців тому +3

    Thank you, IBM, for these videos!!

  • @deyon4521
    @deyon4521 2 роки тому +43

    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 роки тому +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 роки тому +1

      Elementary my dear Deyon nice one.

    • @sc1ss0r1ng
      @sc1ss0r1ng 2 роки тому +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 Рік тому

      😆

    • @recursosmusicales399
      @recursosmusicales399 Рік тому

      Is a fake 😱🤣

  • @huynhphanngockhang5733
    @huynhphanngockhang5733 9 місяців тому +1

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

  • @nokostunes
    @nokostunes 2 роки тому +5

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

  • @AishaKyes
    @AishaKyes 2 роки тому +11

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

  • @aryanarya72
    @aryanarya72 9 місяців тому

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

  • @robertdTO
    @robertdTO 7 місяців тому

    Excellent, clear, to the point in introducing GAN.

  • @KW-md1bq
    @KW-md1bq 2 роки тому +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 місяців тому +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.

  • @kitrt
    @kitrt 3 роки тому +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?

  • @gurukiranhr
    @gurukiranhr 20 днів тому

    Very well explained with simple language!

  • @MOHAMEDNAFILASHIFM
    @MOHAMEDNAFILASHIFM 2 місяці тому

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

  • @elizacampillo7494
    @elizacampillo7494 19 днів тому

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

  • @GigaMarou
    @GigaMarou 2 роки тому +3

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

  • @gauravpoudel7288
    @gauravpoudel7288 10 місяців тому +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 місяців тому

      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.

  • @andyjc9558
    @andyjc9558 2 роки тому +1

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

  • @iverjohansolheim5172
    @iverjohansolheim5172 5 місяців тому

    Very pedagogical setup, loved it!

  • @JohannesNürnberg-c8z
    @JohannesNürnberg-c8z 9 місяців тому

    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

  • @sathirawijeratne7872
    @sathirawijeratne7872 10 місяців тому +1

    Love this explanation!

  • @usamazahid1
    @usamazahid1 2 роки тому +2

    elegant explanation .....great job

  • @monicamateu3750
    @monicamateu3750 Місяць тому

    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..?

  • @tanezcorvideos
    @tanezcorvideos Рік тому +1

    Really perfect explanation of GAN, well done!!

  • @lethane11
    @lethane11 2 роки тому +2

    Superbly explained. Thank you

  • @Has_Le_India13
    @Has_Le_India13 Рік тому

    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

  • @blumehao
    @blumehao 2 роки тому +1

    you use right hand?

  • @MasoodOfficial
    @MasoodOfficial 2 роки тому +2

    Excellent Explanation!

  • @Surya25398
    @Surya25398 2 роки тому +2

    It is really helpful, thanks for your video

  • @DilawarShah-g9f
    @DilawarShah-g9f Рік тому

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

  • @Aimeecroft
    @Aimeecroft 9 місяців тому

    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 роки тому +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 роки тому +4

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

    • @reggaemarley4617
      @reggaemarley4617 2 роки тому +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.

  • @apdy1095
    @apdy1095 2 роки тому +1

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

  • @fundatamdogan
    @fundatamdogan 2 роки тому +1

    I loved the lesson.But GANs more :)

  • @AixinJiangIvy
    @AixinJiangIvy 10 місяців тому

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

  • @syedmuhammadsameer8299
    @syedmuhammadsameer8299 Рік тому

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

  • @saharghassabi
    @saharghassabi 7 місяців тому

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

  • @yasithudawatte8924
    @yasithudawatte8924 2 роки тому +2

    Very well explained😇, thank you.

  • @Democracy_Manifest
    @Democracy_Manifest Рік тому +1

    Great video, perfect presentation. Was this artificially generated?

  • @animanaut
    @animanaut Рік тому

    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

  • @BintAlAbla1999
    @BintAlAbla1999 2 роки тому +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 роки тому

      Have you found your answer yet?

  • @petchpaitoon
    @petchpaitoon 3 роки тому +3

    Thank you, It is informative

  • @jasonchen7758
    @jasonchen7758 2 роки тому +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?

  • @Evokus
    @Evokus 2 роки тому

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

    • @uday3350
      @uday3350 Рік тому +1

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

    • @tudorrad5933
      @tudorrad5933 Рік тому

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

    • @Billy-sm3uu
      @Billy-sm3uu Рік тому +1

      he wrote with his right hand then mirrored the video

  • @Callmejz.ai01
    @Callmejz.ai01 Рік тому

    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

  • @somuchtech9864
    @somuchtech9864 Рік тому

    Very well explained. Thanks for sharing

  • @taqiadenal-shameri3800
    @taqiadenal-shameri3800 Рік тому

    Amazing explanation

  • @usama57926
    @usama57926 2 роки тому +1

    good explanation

  • @sapnilpatel1645
    @sapnilpatel1645 Рік тому

    Very Informative video.Thanks for making it.

  • @mhmoudkhadija3839
    @mhmoudkhadija3839 Рік тому

    Very nice explanation! Thanks sir

  • @uurv
    @uurv 2 роки тому +1

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

    • @hassanbinali1999
      @hassanbinali1999 2 роки тому +1

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

  • @mddildarmandal9241
    @mddildarmandal9241 4 місяці тому

    Interesting , learnt something new

  • @Krunkbitmos
    @Krunkbitmos 8 місяців тому

    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 2 місяці тому

      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

  • @asteralebel2856
    @asteralebel2856 Місяць тому

    what is BigGan and Stylegan?

  • @johnspivack
    @johnspivack 8 місяців тому

    Good explanations. Thanks.

  • @Zackemcee1
    @Zackemcee1 Рік тому

    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

  • @storytimewithme2
    @storytimewithme2 Рік тому

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

  • @neuronai-deon
    @neuronai-deon 24 дні тому

    i love this guy

  • @RuiMartins
    @RuiMartins 2 роки тому +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.

  • @keshavmiglani2697
    @keshavmiglani2697 Рік тому

    Did DALL-E 2 use GAN?

  • @basedmatt
    @basedmatt Рік тому

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

  • @sitrakaforler8696
    @sitrakaforler8696 Рік тому

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

  • @alaad1009
    @alaad1009 Рік тому

    Excellent video

  • @subodhi6
    @subodhi6 2 роки тому +2

    Thank you..!

  • @EmpoweredWithZarathos2314
    @EmpoweredWithZarathos2314 Рік тому

    Loved it😅

  • @myentropyishigh8708
    @myentropyishigh8708 4 місяці тому

    thank you sir!.

  • @yuvrajanand1991
    @yuvrajanand1991 Рік тому

    Simply Loved it

  • @java2379
    @java2379 Рік тому

    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 🙂

  • @minjun9900
    @minjun9900 4 місяці тому

    was really helpful

  • @croom0101
    @croom0101 20 днів тому

    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?

  • @leif1075
    @leif1075 Рік тому

    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..

  • @abdurrouf4159
    @abdurrouf4159 10 місяців тому

    Well explained.

  • @whatnext767
    @whatnext767 3 місяці тому

    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

  • @debayanguha3026
    @debayanguha3026 2 роки тому +1

    thank you ,it's great ...!

  • @heidikeller50
    @heidikeller50 Рік тому

    Super- thank you :)

  • @MdAbdullah-gn6uj
    @MdAbdullah-gn6uj 8 місяців тому

    Nice video

  • @erikschiegg68
    @erikschiegg68 2 роки тому +1

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

    • @sc1ss0r1ng
      @sc1ss0r1ng 2 роки тому

      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.

  • @saifshaikh8679
    @saifshaikh8679 6 місяців тому

    Are Generators used for creating deep fakes?

  • @golamrob
    @golamrob 6 місяців тому

    excellent

  • @sharongreenlaw8096
    @sharongreenlaw8096 25 днів тому

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

  • @DavOlek_ua
    @DavOlek_ua 3 роки тому +2

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

    • @IBMTechnology
      @IBMTechnology  3 роки тому +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 3 роки тому +1

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

  • @fastrobreetus
    @fastrobreetus 2 місяці тому

    TY

  • @prateekkatiyar9532
    @prateekkatiyar9532 3 роки тому +2

    Great

  • @arambhsharma2050
    @arambhsharma2050 3 місяці тому

    yeah the bottom stripe, oh my oh my what i wouldnt give, Mr Whimp says that if a guy notices waist to hip ratio he is checking the birthing ability

  • @sharongreenlaw8096
    @sharongreenlaw8096 25 днів тому

    Have we started mining yet?

  • @drakefruit
    @drakefruit 2 роки тому +2

    how do you write backwards so well lol

  • @mewtu5817
    @mewtu5817 Рік тому

    A gan is a speedcube

  • @--Dipanshu--
    @--Dipanshu-- 10 місяців тому

    how is he writing backwards?

    • @aryanarya72
      @aryanarya72 9 місяців тому

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

  • @MdAbdullah-gn6uj
    @MdAbdullah-gn6uj 8 місяців тому

    Nice

  • @THEMATT222
    @THEMATT222 2 роки тому +1

    Noice 👍 Doice 👍 Ice 👍

  • @techwithbube
    @techwithbube 3 роки тому +3

    First to comment .

  • @IshanJawade
    @IshanJawade 6 місяців тому

    How can he write upside down

  • @VelvetWraith-i3z
    @VelvetWraith-i3z Місяць тому

    great