What are GANs (Generative Adversarial Networks)?

[@baqirhussein1109]

I like the way he smiles and the calm talking

[@canaldot.5243]

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

[@ahmedaj2000]

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

[@SB-yd4tc]

IBM and specifically this video series is my favorite resource to come to for learning AI/ML related concepts. Great information, well explained and love. This person exemplifies the joy of learning.

[@julesnzietchueng6671]

He clearly loves his job and its communicative ^^

[@skycellinium]

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]

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

[@TheAkdzyn]

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]

this is what you call a clear explanation, thanks

[@IBMTechnology]

Glad it helped!

[@xmlviking]

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]

damn

[@deyon4521]

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]

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]

Elementary my dear Deyon nice one.

[@sc1ss0r1ng]

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]

😆

[@recursosmusicales399]

Is a fake 😱🤣

[@AishaKyes]

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

[@jayanthmankavil]

Thank you, IBM, for these videos!!

[@nokostunes]

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

[@aryamahima3]

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

[@kitrt]

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?

[@gauravpoudel7288]

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]

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.

[@huynhphanngockhang5733]

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

[@robertdTO]

Excellent, clear, to the point in introducing GAN.

[@aryanarya72]

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

[@GigaMarou]

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

[@engin-hearing5978]

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]

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

[@reggaemarley4617]

@@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.

[@tanezcorvideos]

Really perfect explanation of GAN, well done!!

[@lethane11]

Superbly explained. Thank you

[@MOHAMEDNAFILASHIFM]

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

[@gurukiranhr]

Very well explained with simple language!

[@Surya25398]

It is really helpful, thanks for your video

[@usamazahid1]

elegant explanation .....great job

[@iverjohansolheim5172]

Very pedagogical setup, loved it!

[@saharghassabi]

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

[@yasithudawatte8924]

Very well explained😇, thank you.

[@Democracy_Manifest]

Great video, perfect presentation. Was this artificially generated?

[@JohannesNürnberg-c8z]

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

[@alanatureza]

Very good explanation! It's easy to understand. Thank you very much! How do you write on the video? I'm super curious to know if it's a program or you are really writing like a mirror

[@Has_Le_India13]

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]

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

[@syedmuhammadsameer8299]

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

[@notQuiteElite7872]

Love this explanation!

[@AixinJiangIvy]

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

[@elizacampillo7494]

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

[@BintAlAbla1999]

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]

Have you found your answer yet?

[@blumehao]

you use right hand?

[@sapnilpatel1645]

Very Informative video.Thanks for making it.

[@monicamateu3750]

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..?

[@ardzzz1008]

specifically 8-bit bitmap format using the .DIB extension

[@MasoodOfficial]

Excellent Explanation!

[@cryptoinside8814]

So you manually adjust generator and discriminator ?

[@apdy1095]

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

[@animanaut]

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]

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

[@somuchtech9864]

Very well explained. Thanks for sharing

[@SantanuKar-h9i]

Very nice articulation !

[@fundatamdogan]

I loved the lesson.But GANs more :)

[@jasonchen7758]

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

[@zlygerda]

Flipped

[@mhmoudkhadija3839]

Very nice explanation! Thanks sir

[@Callmejz.ai01]

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

[@Aimeecroft]

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?

[@petchpaitoon]

Thank you, It is informative

[@Krunkbitmos]

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]

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

[@taqiadenal-shameri3800]

Amazing explanation

[@uurv]

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

[@hassanbinali1999]

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

[@sitrakaforler8696]

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

[@johnspivack]

Good explanations. Thanks.

[@Zackemcee1]

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

[@basedmatt]

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

[@Evokus]

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

[@uday3350]

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

[@tudorrad5933]

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

[@Billy-sm3uu]

he wrote with his right hand then mirrored the video

[@storytimewithme2]

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

[@asteralebel2856]

what is BigGan and Stylegan?

[@croom0101]

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?

[@usama57926]

good explanation

[@keshavmiglani2697]

Did DALL-E 2 use GAN?

[@leif1075]

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..

[@KW-md1bq]

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]

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.

[@java2379]

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 🙂

[@alaad1009]

Excellent video

[@yuvrajanand1991]

Simply Loved it

[@RuiMartins]

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.

[@mddildarmandal9241]

Interesting , learnt something new

[@cryptoinside8814]

So what are the ATTRIBUTES is the key to discriminator. How do you define ATTRIBUTES of a hot dog ?

[@debayanguha3026]

thank you ,it's great ...!

[@neuronai-deon]

i love this guy

[@saifshaikh8679]

Are Generators used for creating deep fakes?

[@EmpoweredWithZarathos2314]

Loved it😅

[@heidikeller50]

Super- thank you :)

[@DavOlek_ua]

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

[@IBMTechnology]

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

[@DavOlek_ua]

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

[@subodhi6]

Thank you..!

[@whatnext767]

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

[@abdurrouf4159]

Well explained.

[@minjun9900]

was really helpful

[@--Dipanshu--]

how is he writing backwards?

[@aryanarya72]

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

[@myentropyishigh8708]

thank you sir!.

[@erikschiegg68]

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

[@sc1ss0r1ng]

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.

[@THEMATT222]

Noice 👍 Doice 👍 Ice 👍

[@drakefruit]

how do you write backwards so well lol

[@IshanJawade]

How can he write upside down

[@benatkinson3160]

He would’ve just mirrored the video

[@MdAbdullah-gn6uj]

Nice video

[@sharongreenlaw8096]

Have we started mining yet?

[@Steppinonshii]

what type of magis is this . he is writing backwards

[@IBMTechnology]

See ibm.biz/write-backwards for the backstory

[@Steppinonshii]

@@IBMTechnology omg 🤣🤦‍♂️

[@sharongreenlaw8096]

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

[@arambhsharma2050]

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

[@TheSouthernSiren]

I've had a few supervisors that I'm sure were fake samples.😐