YouSaid · the spoken record

Ian Goodfellow

lines on the record: 86
first: 2019-04-18
most recent: 2019-04-18
sittings or episodes: 1
sources: podcast

Every line below is reproduced as it was said and linked to the record it came from. Nothing here is summarised or generated. Directory · Search · Corrections

“I think so, yeah, yeah. Like one methodology that I think is not a specific methodology, but like a category of solutions that I'm excited about today is making dynamic models that change every time they make a prediction. So, right now, we tend to train models, and then after they're trained, we freeze them and we just use the same rule to classify everything that comes in from then on. That's really a sitting duck from a security point of view. If you always output the then people can just run inputs through until they find a mistake that benefits them. And then they use the same mistake over and over and over again. I think having a model that updates its predictions so that it's harder to predict what you're going to get will make it harder for an adversary to really take control of the system and make it do what they want it to do.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“I guess I'm most concerned about domains we haven't really encountered yet. Imagine 20 years from now when we're using advanced AIs to do things we haven't even thought of yet. Like if you ask people what are the important problems in security of phones in like 2002, I don't think we would have anticipated that we're using them for nearly as many things as we're using them for today. I think it's going to be like that with AI that you can kind of try to speculate about where it's going, but really the business opportunities that end up taking off. Would be hard to predict ahead of time. What you can predict ahead of time is that almost anything you can do with machine learning, you would like to make sure that people can't get it to do what they want rather than what you want just by showing it a funny QR code or a funny input pattern.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“I think resistance to adversarial examples, figuring out how to make machine learning secure against an adversary who wants to interfere it and control with it is one of the most important things researchers today could solve.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“So proving that I'm not a robot with today's technology, that's pretty straightforward. My conversation today hasn't veered off into, you know. Talking about the stock market or something because of my training data. But I guess more generally trying to prove that something is real from the content alone is incredibly hard. That's one of the main things I've gotten out of my GAN research that Can simulate almost anything, and so you have to really step back to a separate channel to prove that something is real. So I guess I should have had myself stamped on a blockchain when I was born or something. But I didn't do that. So according to my own research methodology, there's just no way to know at this point.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Or, like you type in a paragraph explaining what you want it to do and it figures out what web searches it should run and downloads all the necessary ingredients.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Something knows how to preprocess the data so that it successfully accomplishes the task, then it would be very hard to argue that it doesn't truly understand the task in some fundamental sense. I don't necessarily know that that's like the philosophical definition of intelligence, but that's something that would be really cool to build, that would be really useful, and would impress me and would convince me that we've made a step forward in real AI.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“AutoML has mostly been moving toward once we've built all the glue, can the machine learning system design the architecture really well? And so I'm more of saying like.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Something that doesn't take a lot of glue from human engineers. So imagine that instead of having to go to the CFAR website and download CFAR 10 and then write a Python script to parse it and all that, you could just point an agent at the CFAR10 problem and it downloads and extracts the data and trains a model and starts giving you predictions. I feel like something that doesn't need to have every step of the pipeline assembled for it. Definitely understands what it's doing.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“They tend to be similar environments. All of them are playing an action based video game. We don't really have an agent that goes from playing a video game to reading the Wall Street Journal to predicting how effective a molecule will be as a drug or something like that.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Supposed to print. I think it's a necessary ingredient. Yeah, I don't think that we're going to get to artificial general intelligence by training on fixed data sets or by thinking really hard about the problem. I think that the agent really needs to interact and have a variety of experiences within the same lifespan. And today we have many different models that can each do one thing, and we tend to train them on one data set or one RL environment. Sometimes there are actually papers about getting one set of parameters to perform well in many different RL environments, but we don't really have anything like an agent that goes seamlessly from one type of experience to another and really integrates all the different things that it does over the course of its life. When we do see multi-agent environments, they tend to be, or many multi-environment agents.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“I think that it definitely takes a better environment than we currently have for training agents, that we want them to have a really wide diversity of experiences. I also think it's going to take really a lot of computation. It's hard to imagine exactly how much.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Right now, we all talk a lot about how interpretable different machine learning algorithms are, but it's really just people's opinion, and everybody probably has a different idea of what interpretability means. If we could define some concept related to interpretability that's actually measurable, that would be a huge leap forward, even without a new algorithm that increases that quantity. And also once we had the definition of differential privacy, it was fast to get the algorithms that guaranteed it. So you could imagine once we have definitions of good concepts and interpretability, we might be able to provide the algorithms that have the interpretability guarantees quickly too.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, so I think fairness and interpretability are areas where we just really don't have any idea how anything should be done yet. Like for interpretability, I don't think we even have the right definitions. And even just defining a really useful concept. You don't even need to run any experiments could have a huge impact on the field. We've seen that, for example, in differential privacy, that Cynthia Dwark and her collaborators made this technical definition of privacy, where before a lot of things were really mushy. And then with that definition, you could actually design randomized algorithms for accessing databases and guarantee that they preserved individual people's privacy in a mathematical quantitative sense.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, I do think that there are a lot of ideas that can be developed really quickly. Gowns were probably a little bit of an outlier on the whole one hour time scale But just in terms of low resource ideas where you do something really different on the algorithm scale and get a big payback, I think it's not as likely that you'll see that in terms of things like core machine learning technologies, like a better classifier or a better reinforcement learning algorithm or a better generative model. If I had the GAN idea today, it would be a lot harder to prove that it was useful than it was back in 2014 because I would need to get it running on something like ImageNet or Celeb A at high resolution. Those take a while to train. You couldn't train it in an hour and know that it was something really new and exciting. Back in 2014, training on Amnesty was enough. But there are other areas of machine learning where I think a new idea could actually be developed really quickly with low resources.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Somebody who knew the appropriate private key for this phone was actually able to sign this image and upload it to this server at this timestamp. So, you could imagine maybe you make phones that have the private keys hardware embedded in them. If a state security agency really wants to infiltrate the company, they could probably plant a private key of their choice or break open the chip and learn the private key or something like that. But it would make it a lot harder for an adversary with fewer resources to fake things.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“I don't think we'll ever be able to look at the pixels of a photo and tell you for sure that it's real or not real. And I think it would actually be somewhat dangerous to rely on that approach too much. If you make a really good fake detector and then someone's able to fool your fake detector and your fake detector says this image is not fake, then it's even more credible than if you've never made a fake detector in the first place. What I do think we'll get to is systems that we can kind of use behind the scenes to make estimates of what's going on and maybe not use them in court for a definitive analysis. I also think we will likely get better authentication systems where imagine that every phone cryptographically signs everything that comes out of it. You won't be able to conclusively tell that an image was real, but you would be able to tell”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“I'm a lot less concerned about 20 years from now than the next few years. I think there will be a kind of bumpy cultural transition as people encounter this idea that there can be very realistic videos and audio that aren't real. I think 20 years from now, people will mostly understand that you shouldn't believe something is real just because you saw a video of it. People will expect to see that it's been cryptographically signed or have some other mechanism to make them believe that the content is real. There's already people working on this. There's a startup called TruePick that provides a lot of mechanisms for authenticating that an image is real. There may be not quite up to having a state actor try to evade their verification techniques. But it's something that people are already working on and I think we'll get right eventually.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Another way I think that GANS in particular could be used for fairness would be to make something like a cycle GAN where you can take data from one domain and convert it into another. We've seen cycleGAN turning horses into zebras. We've seen other unsupervised GANs made by Ming Yu, Lu doing things like turning day photos into night photos. I think for fairness, you could imagine taking records for people in one group and transforming them into analogous people in another group and testing to see if they're treated equitably across those two groups. There's a lot of things that would be hard to get right to make sure that the conversion process itself is fair. And I don't think it's anywhere near something that we could actually use yet. But if you could design that conversion process very carefully, it might give you a way of doing audits where you say, what if we took people from this group, converted them into equivalent people in a”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“So, what you'd like to do is make a machine learning model that can still take in a lot of different attributes and make a really accurate informed prediction, but be confident that it isn't reverse engineering gender or another sensitive variable internally. You can do that using something very similar to the domain adversarial approach, where you have one player that's a feature extractor and another player that's a feature analyzer. And you want to make sure that the feature analyzer is not able to guess the value of the sensitive variable that you're trying to keep private.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, so there's a paper from Amos Storky's lab about how to learn machine learning models that are incapable of using specific variables. So say, for example, you wanted to make predictions that are not affected by gender. It isn't enough to just leave gender out of the input to the model. If their name is Ian, they're kind of obviously a man.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, in a way. I think that could generalize better. The other thing that GANS are really good for is not necessarily generating new data that's exactly like what you already have, but by generating new data that has different properties from the data you already had. One thing that you can do is you can create differentially private data. So suppose that you have something like medical records and you don't want to train a classifier on the medical records and then publish the classifier because someone might be able to reverse engineer some of the medical records you trained on. There's a paper from Casey Green's lab that shows how you can train again using differential privacy. And then the samples from the GAN still have the same differential privacy guarantees as the parameters of the GAN. So you can make fake patient data for other researchers to use. And they can do almost anything they want with that data because it doesn't come from real people and the differential”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“A whole lot of different generative models on the same training set, create samples from all of them, and then train a classifier on that. Because each of the generative models might generalize in a slightly different way, they might capture many different axes of variation that one individual model wouldn't. And then the classifier can capture all of those ideas by training on all of their data. So it would be a little bit like making an ensemble of classifiers. And I think that...”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, one thing you could hope for with GANS is you could imagine I've got a limited training set and I'd like to make more training data to train something else like a classifier. Could train the GAN on the training set and then create more data. And then maybe the classifier would perform better on the test set after training on those bigger GAN generator data set. So that's the simplest version of something you might hope would work. I've never heard of that particular approach working, but I think there's some closely related things that I think could work in the future and some that actually already have worked. So if we think a little bit about what we'd be hoping for if we use the GAN to make more training data, we're hoping that the GAN will generalize to new examples better than the classifier would have generalized if it was trained on the same data. And I don't know of any reason to believe that the GAN would generalize better than the classifier would. But what we might hope for is that the GAN could generalize differently from a specific classifier. So one thing I think is worth trying that I haven't personally tried, but someone could try is what if you try”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“The features came from. So it's a lot like the real versus fake discriminator in GANS. And then the feature extractor, you can think of as loosely analogous to the generator in GANS, except what it's trying to do here is both fool the domain recognizer into not knowing which domain the data came from and also extract features that are good for classification. So at the end of the day, in the cases where it works out, you can actually get features that work about the same in both domains. Sometimes this has a drawback where in order to make things work the same in both domains, it just gets worse at the first one. But there are a lot of cases where it actually works out well on both.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Like ImageNet, but then deploy on users' phones where the user is taking pictures in the dark and pictures while moving quickly and just pictures that aren't really centered or composed all that well. When you take a normal machine learning model, it often degrades really badly when you move to the new domain because it looks so different from what the model was trained on. Domain adaptation algorithms try to smooth out that gap. And the domain adversarial approach is based on training a feature extractor where the features have the same statistics regardless of which domain you extracted them on. So in the domain adversarial game, you have one player that's a feature extractor and another player that's a domain recognizer. The domain recognizer wants to look at the output of the feature extractor and guess which of the two domains.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, the one that I spend most of my time on is in security. You can model most interactions as a game where there's attackers trying to break your system and the defender trying to build a resilient system. There's also domain adversarial learning, which is an approach to domain adaptation that looks really a lot like GANS. The authors had the idea before the GAN paper came out. Their paper came out a little bit later. And they were very nice and cited the GAN paper, but I know that they actually had the idea before it came out. Domain adaptation is when you want to train a machine learning model in one setting called a domain and then deploy it in another domain later. And you would like it to perform well in the new domain, even though the new domain is different from how it was trained. So for example, you might want to train on a really clean image data set.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“And they do that essentially using a clustering algorithm where the discriminator learns to assign the objects to groups. And then this understanding that objects can be grouped into similar types helps it to form more realistic ideas of what should be appearing in the image because it knows that every image it creates has to come from one of these archetypal groups rather than just being some arbitrary image. If you train a GAN with no class labels, you tend to get things that look sort of like grass or water or brick or dirt, but without necessarily a lot going on in them. And I think that's partly because if you look at a large image net image, the object doesn't necessarily occupy the whole image. And so you learn to create realistic sets of pixels, but you don't necessarily learn the object is the star of the show.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, some researchers at Brain Zurich actually just released a really great paper on semi-supervised GANs where their goal isn't to classify, it's to make recognizable objects despite not having a lot of labeled data. They were working off of DeepMind's Big GAN project, and they showed that they can match the performance of Big Gan using only 10%, I believe, of the labels. Big GAN was trained on the ImageNet data set, which is about This latest project from Brain Zurich shows that they're able to get away with only having about 10% of the images labeled.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“So, for example, for the MNIS dataset, you want to look at an image of a handwritten digit and say whether it's a zero, a one, or a two, and so on. To get down to less than 1% accuracy required around 60,000 examples until maybe about 2014 or so. In 2016 with this semi-supervised GAN project, Tim was able to get below 1% error using only 100 labeled examples. So that was about a 600x decrease in the amount of labels that he needed. He's still using more images than that, but he doesn't need to have each of them labeled as, you know, this one's a one, this one's a two, this one's a zero, and so on.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“My colleague at OpenAI, Tim Solomons, who's at Brain Now, wrote a paper called Improve Techniques for Training GANs. I'm a co-author on this paper, but I can't claim any credit for this particular part. One thing he showed in the paper is that you can take the GAN discriminator and use it as a classifier that actually tells you this image is a cat, this image is a dog, this image is a car, this image is a truck. And so not just to say whether the image is real or fake, but if it is real to say specifically what kind of object it is. And he found that you can train these classifiers with far fewer labeled examples than traditional classifiers.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, yeah. And so from there, I would say some interesting things we've seen are. A lot you can say about how just the quality of standard image generation GANs has increased, but what's also maybe more interesting on an intellectual level is how the things you can use GANS for has also changed. One thing is that you can use them to learn classifiers without having to have class labels for every example in your training set. So that's called semi-supervised learning.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Process actually generate realistic images of faces and things like that. That was sort of like the beginning of the Cambrian explosion of Gans. Once you had animals that had a backbone, you suddenly got lots of different versions of fish and. Four-legged animals and things like that. So DC GAN became kind of the backbone for many different models that came out.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“And that got a lot of us excited. One of the next really big steps was Lapgan by Emily Denton and Sumith Chintala at Facebook AI Research, where they actually got really good high resolution photos working with Gans for the first time. They had a complicated system where they generated the image starting at low res and then scaling up to high res, but they were able to get it to work. In 2015, I believe later that same year Alec Radford and Sumith Chintala and Luke Metz published the DC GAN paper, which it stands for Deep Convolutional GAN. It's kind of a non-unique name because these days basically all GANs and even some before that were deep in convolutional, but they just kind of picked a name for a really great recipe where they were able to actually, using only one model instead of a multistep.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“We use MNIST, which is little handwritten digits. We use the Toronto Face database, which is small grayscale photos of faces. We did have recognizable faces. My colleague Bing Shu put together the first GAN face model for that paper. We also had the CFAR 10 data set, which is things like very small 32 by 32 pixels of cars and cats and dogs. For that, we didn't get recognizable objects, but all the deep learning people back then were really used to looking at these failed samples and kind of reading them like tea leaves. And people who are used to reading the tea leaves recognize that our tea leaves at least look different. Maybe not necessarily better, but there was something unusual about them.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, so a few highlights. In the first paper, we just showed that GANs basically work. If you look back at the samples we had now, they look terrible. On the CFAR10 dataset, you can't even recognize objects in them.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Or are gans doing better because they prioritize the realism of samples? Over the accuracy of the density function. I think all of those are potentially valid explanations. And it's hard to tell.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, or like the kind of expertise. So, a lot of people who've traditionally been excited about graphics or art and things like that have gotten interested in GANS. And to some extent, it's hard to tell. Argans doing better because they have a lot of graphics and art experts behind them. Or are GANs doing better because they're more computationally efficient?”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“They're reasonable. Yeah. I would say a lot of the best results are from GANS these days, but it can be hard to tell How much of that is based on who's studying which type of algorithm, if that makes sense.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Likelihood. One approach is to very carefully design the model so that it is computationally tractable to measure the density assigns to a particular point. So there are things like autoregressive models like pixel CNN. Those basically break down the probability distribution into a product over every single feature. So for an image, you estimate the probability of each pixel given all of the pixels that came before it. There's tricks where if you want to measure the density function, you can actually calculate the density for all these pixels more or less in parallel. Generating the image still tends to require you to go one pixel at a time, and that can be very slow. But there are, again, tricks for doing this in a hierarchical pattern where you can keep the runtime under control.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah. So it's maybe a little bit easier to start with what kinds of generative models are there other than GANS. So most generative models are likelihood-based. Where to train them, you have a model that tells you how much probability it assigns to a particular example. And you just maximize the probability assigned to all the training examples. It turns out that it's hard to design a model that can create really complicated images or really complicated audio waveforms and still have it be possible to estimate the likelihood function from a computational point of view. Most interesting models that you would just write down intuitively, it turns out that it's almost impossible to calculate the amount of probability they assign to a particular point. So there's a few different schools of generative models in the light.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“That would imply that it would be much harder to make generative models in other domains. So far, we're able to make reasonable speech models and things like that. But to be honest, we haven't actually explored a whole lot of different data sets all that much. We don't, for example, see a lot of deep learning models of biology data sets where you have lots of microarrays measuring the amount of different enzymes and things like that. So we may find that some of the progress that we've seen for images and speech turns out to really rely heavily on the model architecture. And we were able to do what we did for vision by trying to reverse engineer the human visual system. And maybe it'll turn out that we can't just use that same trick for arbitrary kinds of data.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Evolutional net, and you don't even need to learn the parameters of it at all. You just use the model architecture. And it's already useful for things like in painting images. I think that shows us that the convolutional network architecture captures something really important about the structure of images. And we don't need to actually use learning to capture all the information coming out of the convolutional net.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Statistical learning theory sense that you can actually create reasons for why it would require quite a lot of learning steps and a lot of observations of different latent variables before you can memorize the training data. That still doesn't really explain why when you produce samples that are new, why do you get compelling images rather than just garbage that's different from the training set? And I don't think we really have a good answer for that. Especially if you think about how many possible images are out there and how few images the generative model sees during training, it seems just unreasonable that generative models create new images as well as they do, especially considering that we're basically training them to memorize rather than generalize. I think part of the answer is there's a paper called Deep Image Prior where they show that you can take a convo.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Models that are based on maximizing the likelihood, the way that you obtain the maximum likelihood for a specific training set is you assign all of your probability mass to the training examples and nowhere else. For GANS, the game is played using a training set. So the way that you become unbeatable in the game is you literally memorize training examples. One of my former interns wrote a paper. His name is Vaishnav Nagarajan, and he showed that it's actually hard for the generator to memorize the training data, hard in a”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, and not just to flatter my own work, but generative models, all of them have this property that if they really did what we ask them to do, they would do nothing but memorize the training data.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“As the two players compete in this game, the discriminator tries to become better at recognizing whether images are real or fake, and the generator becomes better at fooling the discriminator into thinking that its outputs are real. And you can analyze this through the language of game theory and find that there's a Nash equilibrium where the generator has captured the correct probability distribution. So in the cat example, it makes perfectly realistic cat photos. And the discriminator is unable to do better than random guessing because all the samples coming from both the data and the generator look equally likely to have come from either source.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Process, it'll just produce completely random images. The other player is called the discriminator. The discriminator takes images as input and guesses whether they're real or fake. You train it both on real data, so photos that come from your training set, actual photos of cats, and you train it to say that those are real. You also train it on images that come from the generator network, and you train it to say that those are fake.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“They do that completely from scratch. It's analogous to human imagination when again creates a new image of a cat. It's using a neural network to produce a cat that has not existed before. It isn't doing something like compositing photos together. You're not literally taking the eye off of one cat and the ear off of another cat. It's more of this digestive process where the neural net trains in a lot of data and comes up with some representation of the probability distribution and generates entirely new cats. There are a lot of different ways of building a generative model. What's specific to GANS is that we have a two-player game in the game theoretic sense. And as the players in this game compete, one of them becomes able to generate realistic data. The first player is called the generator. It produces output data, such as just images, for example. And at the start of the learning process,”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, so generative adversarial networks are a particular kind of generative model. A generative model is a machine learning model that can train on some set of data. Like say you have a collection of photos of cats and you want to generate more photos of cats, or you want to estimate a probability distribution over cats so you can ask how likely it is that some new image is a photo of a cat. GANs are one way of doing this. Some generative models are good at creating new data. Other generative models are good at estimating that density function and telling you how likely particular pieces of data are to come from the same distribution as the training data. GANs are more focused on generating samples rather than estimating the density function. There are some kinds of GANs like flow GAN that can do both, but mostly GANs are about generating samples, generating new photos of cats that look realistic.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source
“A lot of the time with machine learning algorithms, it's really hard to predict ahead of time how well they'll actually perform. Have to just run the experiment and see what happens. And I would say I still today don't have like one factor I can put my finger on and say this is why GANS worked for photo generation and deep bolts and machines don't. There are a lot of theory papers showing that under some theoretical settings, the GAN algorithm does actually converge. Those settings are That they don't necessarily explain the whole picture in terms of all the results that we see in practice.”
2019-04-18 · Lex Fridman Podcast · Ian Goodfellow: Generative Adversarial Networks (GANs) · IDENTIFIED FROM THE TRANSCRIPT · source