YouSaid · the spoken record

Tomaso Poggio

lines on the record: 73
first: 2019-01-19
most recent: 2019-01-19
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

“Yeah, absolutely. I also spent some time in Germany again. There is this tradition in which people are more forthright, less kind than here. In the US, when you write a bad letter, you still say this guy is nice.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“It's partly repeating what I said about an environment that should be friendly and fun and ambitious. I think I learned a lot from some of my advisors and friends and some who are physicists. And there was, for instance, this... Behavior that was encouraged when somebody comes with a new idea in the group, unless it's really stupid, but you are always enthusiastic. And you are enthusiastic for a few minutes, for a few hours. Then you start. Asking critically a few questions, testing this But, you know, this is a process that is, I think, very good. You have to be enthusiastic. Sometimes people are very critical from the beginning. That's not.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“Well, of course, you know, it's being curious in an active and ambitious way, yes. And definitely. But I think sometime in science, there are friends of mine who are like There are some of the scientists like to work by themselves. And kind of communicate only when they complete their work or discover something. I think I always found the actual process of discovering something is more fun if it's together with intelligent and curious and fun people.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“Microphones for receiving. So their sensory system was there. And the impression of all the subject, very strong, they could not shake it off was that where the robot was. Could look at themselves from the robot and still feel they were where the robot is. They were looking at their body. Their self had moved”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“Visual intelligence or the visual cortex and And visual intelligence in the sense of how we look around ourselves and understand The world around ourselves, you know, meaning what is going on, how we could go from here to there without heating obstacles, whether there are other agents, people in the environment. These are all things that we perceive very quickly. And it's something actually quite close to being conscious, not quite, but there is this interesting experiment that was run at Google X, which is in a sense is just a virtual reality experiment, but in which they had subject sitting, say, in a chair with goggles like Oculus and so on. Earphon And they were seeing through the eyes of a robot nearby to cameras.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“Well, of course, I'm excited about one of the moonshots, which is our Center for Brains, Minds, and Machines. The one which is fully funded by NSF. And it is about visual intelligence.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“Of course, I don't know whether the next breakthroughs, I think that there is a good chance, as I said before, that the next breakthrough will also be inspired by neuroscience. But which one? I don't know.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“I never thought about it. It's a very interesting question. I think Steve Jobs in his commencement speech at Stanford argued that having a finite life was important for stimulating achievements and so on. It was a different.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“We may, yes. So, for instance, I personally think that when Test a machine or a person in a Turing test and an extended Turing test. I think consciousness is part of what we require in that test, you know, implicitly to say that this is intelligent. Christophe disagrees.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“Most of the people working in artificial intelligence, I think, would answer, we don't strictly need consciousness to have an intelligence system.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“It's unclear. So again, this is a deep problem, partly because it's very difficult to define consciousness. And there is a debate among neuroscientists and About whether consciousness and philosophers, of course, whether consciousness is something that requires flesh and blood, so to speak. Could be, you know, we could have silicon devices that are conscious. Or up to statement like everything has some degree of consciousness and some more than others. This is like Giulio Togone and Fi.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“No, that is psychology, but there is also, in the meantime, there is evidence of MRI of specific areas of the brain that are involved in certain ethical judgment. And not only this, you can stimulate those areas with magnetic fields and change the ethical decisions. So that's work by a colleague of mine, Rebecca Sachs. And there is other researchers doing similar work. And I think, you know, this is the beginning. But ideally, at some point we'll have an understanding of how this works and why it evolved, right?”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“And, you know, I think that would be important to understand also for being able to design machines that are ethical machines in our sense of ethics.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“Yes. You know how a neuroscientist should or should not behave. Can think of a neurosurgeon and the ethics rule he has to be or he has to be. But I'm more interested on the neuroscience. You're blowing my mind.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“I think, yeah, ethics is learnable, very likely. I think it's one of these problems where Think understanding Neuroscience of ethics. People discuss there is an ethics of neuroscience.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“Right now, that would be still a powerful understanding if I can build a learning machine, even if I don't understand in detail every time it learns something.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“So many years ago, this was actually, let me see, 40, 41 years ago, I wrote a paper with David Maher, who was one of the founding fathers of computer vision, computational vision. I wrote a paper about levels of understanding, which relates to the question I discussed earlier about understanding PowerPoint, understanding transistors and so on. And, you know, in that kind of framework, we had the level of the hardware and the top level of the algorithms. We did not have learning. Recently, I updated adding levels. And one level I added to those three was Learning. You can imagine you could have a good understanding of how you construct learning machine like we do. But being unable to describe in detail what the learning machines will discover.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“Well, probably no, but again, it depends You really mean for understanding, so I think We don't understand. How deep networks work. I think we are beginning to have a theory now. But in the case of deep networks, or even in the case of the simple kernel machines or linear classifier, we really don't understand the individual units or so. But we understand the computation and the limitations and the properties of it are. It's similar to many things. What does it mean to understand how a fusion bomb works? How many of us... Many of us understand the basic principle. And some of us may understand deeper details.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“To predict, but I would be, but as I said, this is completely, I would be more like... Rodbrooks, the I think he's about 200 years.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“I think that's really wrong. That can be misleading because in terms of priority, we should still be more worried about nuclear weapons and what people are doing about it and so on than AI.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“Nick buster, am I right, you know, and a couple of other people that, for instance, AI is more dangerous than nuclear weapons.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah. I'm not against worrying at Personally, I think that it will take a long time before there is real reason to be worried. But as I said, I think it's good to put in place and think about possible safety against what I find a bit misleading are things like that have been said by people I know, like Elon Musk and what his Bostrom in particular, what his first name.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“No, I think that's a huge gap. I think present algorithm with all the success that we have and the fact that there are a lot of very useful, I think we are in a golden age for applications of low-level vision and low-level speech recognition and so on, Alexa and so on. There are many more things similar level to be done, including medical diagnosis and so on, but we are far from what we call understanding of a scene, of language, of actions, of people that is, despite the claims, that's, I think, very far.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“Right. So it's like looking at an object without backgrounds. Ideal for learning the object, otherwise, it's really difficult because you have so much stuff. So suppose you do this at the beginning, first weeks. Then after that, you can recognize object. Now they are imprinted a number of objects. Even in the background, even without motion.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“Even in the readiness, in the very peripheral part, it's very conserved across species, something that evolution discovered early. It may be the reason why babies tend to look in the first few days to moving objects and not to not moving objects. Now, moving objects means, okay, they are attracted by motion, but motion also means that motion gives automatic segmentation from the background. So, because of motion boundaries, either the object is moving or the eye of the baby is tracking the moving object and the background is moving, right?”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“That's part of the problem. If we look at biology, a reasonable assumption, I think is In the same spirit that I said, evolution is opportunistic and has weak priors. The way I think the intelligence of a child, the baby may develop is by bootstrapping Weak priors from evolution for instance Can assume that you are having most organisms, including human babies, built-in, some basic machinery to detect motion and relative motion. And in fact, there is, you know, we know all insects from fruit flies to other animals, they have this.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“I like that because when Again, one caricature of the history of computer science, you could say, begins with programmers. Expensive Continuous labelers cheap. And the future would be schools like we have for kids.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“But the output was pretty less than gains, but the output was pretty much of the same quality. So I think for computer graphics type application, definitely GANS can be quite useful, and not only for that, but for helping, for instance, on this problem of unsupervised example of reducing the number of labeled examples. I think people, it's like they think they can get out more than they put in.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“I don't think for that problem, which I really think is important, I think they may help, they certainly have applications, for instance, in computer graphics. I did work long ago. Which was a little bit similar in terms of saying, okay, I have a network and I present images and I can input its images and output is, for instance, the pose of the image, a face, a much smiling is rotated 45 degrees or not. What about having a network that I train with the same data set, but now I invert input and output? Now, the input is the pause or the expression, a number, certain numbers, and the output is the image. And I train it. And we did pretty good interesting results in terms of producing. Very realistic looking images. It was less sophisticated mechanism.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“Gains is one way to get estimation of probability densities, which is a somewhat new way that people have not done before. I don't know whether this will really play an important role in intelligence. It's interesting. I'm less enthusiastic about it than many people in the field. The feeling that many people in the field are really impressed by the ability of producing realistic looking images in this generative way.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“What we proved is that if you have deep layers, hierarchical architecture with local connectivity of the type of convolutional deep learning. And if you're dealing with a function that has This kind of hierarchical architecture, then you avoid completely the curse.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“The question, the interesting question is that If this theorem You can approximate, fine. But when you ask how many neurons, for instance, or in the case of how many monomials I need to get a good approximation. Then it turns out that that depends on the dimensionality of your function, how many variables you have. But it depends on the dimensionality of your function in a bad way. For instance, suppose you want an error which is no worse than 10% in your approximation. You come up with a network that approximates your function within 10%. Then turns out that the number of units you need are in the order of 10 to the dimensionality d. How many variables? So if you have two variables, these two and you have 100 units and OK. But if you have, say, 200 by 200 pixel images, now this is 40,000 whatever.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“No, this one, you know, I never found it very surprising. It was known since the 80s, since I entered. Because it's basically the same as Vaestras' theorem, which says that I can approximate any continuous function with a polynomial of sufficient number of terms, monomials. Are basically the same, and the proofs are very similar.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“Pretty good. It's not so surprising, right? It's like, you know, if you have a system of linear equation and you have more unknowns than equations, then you have, we know you have an infinite number of solutions. And the question is to pick one. That's another story. But you have an infinite number of solutions. So there are a lot of value of your unknowns that satisfy the equations.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“Lot of them, so we have a lot of solutions, so it's not so surprising that you can find them relatively easily. This is because of the overparameterization.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“So I think we have some initial understanding why this happens. But one nice side effect of having this overparameterization, more parameters than data, is that when you look for the minima of a loss function, like stochastic gradient descent is doing, you find I made some calculations based on old Basic theorem of algebra called Bezou theorem that gives you an estimate of the number of solutions of a system of polynomial equation. Anyway, the bottom line is that there are probably more minima for a typical deep networks than atoms in the universe. To say there are a lot because of the overparametrization. A more global minimum, zero minimum, good minimum.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“An interesting fact is a change in a sense in how people think about statistics. And this is the following is that Typ When you had And you had, say, a model with parameters, you are trying to fit the model to the data, you know, to fit the parameter. Typically the kind of crowd wisdom type idea was you should have at least twice the number of data than the number of parameters. maybe 10 times is better. Now, the way you train neural network these days is that they have 10 or 100 times more parameters than data. Exactly the opposite. Which has been one of the puzzles about neural networks. How can you get something that really works when you have so much freedom?”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“Yes, so I find neuroscience, the architecture of cortex is really similar to the architecture of deep networks. So there is a nice correspondence there between the biology and this kind of local connectivity hierarchical architecture. The stochastic radiant descent, as you said, is a very simple technique. It seems pretty unlikely that biology could do that from what we know right now about cortex and neurons and synapses. So it's a big question open whether there are other Optimization learning algorithms that can replace stochastic gradient descent. And my guess is But nobody has found yet a real answer. I mean, people are trying, still trying, and there are some interesting ideas. The fact that stochastic gradient descent is so successful, this has become clear is not so mysterious. And the reason is that”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“Maybe the Why we have Local connectivity in the brain, like simple cells in cortex looking only at the small part of the image, each one of them and then other cells looking at the small number of the simple cells and so on. The reason for this... maybe purely that it was difficult to grow long-range connectivity. So suppose it's for biology. It's possible to grow short range connectivity, but not long range also because there is Number of long range that you can. And so you have this limitation from the biology. And this means you build a deep convolutional network. This would be something like a deep convolutional network. And this is great for solving certain class of problems. These are the ones we find easy and important for our life. And yes, they were enough for us to survive”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“And cannot solve problems that don't have this compositional structure. So the problem is we are accustomed to, we think about, we test our algorithms on. Are this composition structure because our brain is made up?”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“Little bit. We agree on most, but the conclusion is a bit different. His conclusion is that for images, for instance, the compositional structure of this function that we have to learn or to solve these problems comes from physics, comes from the fact that you have local interactions in physics between atoms and other atoms between particle of matter and other particles, between planets and other planets, between stars and other. It's all local. And that's true. But you could push this argument a bit farther, not this argument, actually. You could argue that maybe that's part of the truth. But maybe what happens is kind of the opposite, is that our brain is wired up as a deep network. He can learn, understand, solve problems that have this compositional structure.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“Then deep networks are much more powerful than shallow networks to approximate the underlying function. And the particular structure is a structure of compositionality. If the function is made up of functions of function so that you need to look when you are interpreting an image, classifying an image, you don't need to look at all pixels at once, but you can compute something from small groups of pixels, and then you can compute something on the output of this local computation and so on. Is similar to what you do when you read the sentence. You don't need to read the first and the last letter, but you can read syllables, combine them in words, combine the words in sentences. So this is this kind of structure.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“I spoke about I use the term compositionality. When we looked at deep neural networks, multilayers, and trying to understand when and why they are more powerful than more classical one-layer networks like linear classifier or kernel machines, so-called. What we found is that in terms of approximating or learning or representing a function, a mapping from an input to an output, like from an image to the label in the image. If this function has a particular structure”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“I think you can, but it's much more difficult and it's not completely obvious. And as I said, I think it's one of the, personally, I think he's the greatest problem in science. So, you know, I think it's... It's fair that it's difficult. That's a difficult one.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“One but for the brain I think these levels of understanding, so the algorithms, which kind of computation, the equivalent PowerPoint and the circuits, the transistors, I think they are much more intertwined with each other. There is not a neatly level of the software separate from the hardware. And so that's what why I think in the case of the brain the problem is more difficult more than for computers requires the interaction, the collaboration between different types of expertise.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“Very good intelligent processes. So I think in the case of computers because they were made by engineers, by us, this different level of understanding are rather separate on purpose. They are separate modules so that the engineer that designed the circuit for the chips does not need to know what is inside PowerPoint. And somebody you can write a software translating from one to the other. To the other end. So in that case, I don't think understanding the transistor help you understand PowerPoint or very little If you want to understand the computer, this question, you know, I would say you have to understand at different levels if you really want to build.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“Well, in terms of levels of abstraction, I think we need all of them. It's like if you ask me What does it mean to understand a computer? That's much simpler. But in a computer, I could say, well, I understand how to use PowerPoint. That's my level of understanding a computer. It has reasonable. It gives me some power to produce lights and beautiful. Now, could I ask somebody else who says, well, I know how the transistor work that are inside the computer. I can write the equation for transistor and diodes and circuits, logical circuits. And I can ask this guy, do you know how to operate PowerPoint? No idea.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“So we know quite a bit at the same time we don't know a lot, but the bit we know. In a sense, we know a lot of the details and men we don't know and we know a lot of the top level, the answer to the top level question, but we don't know some basic ones, even in terms of general neuroscience, forgetting vision. Why do we sleep? It's such a basic question. And we really don't have an answer to that.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“The cortex, I think your question about hardware and software and learning and so on, I think it's rather open. And I find very interesting for Isa to think about an architecture, computer architecture that is good for vision and at the same time is good for language. Seems to be so different problem areas that you have to solve.”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source
“That's a great question. So, there are parts of the brain. Like the cerebellum or the hippocampus that are quite different from each other. They clearly have different anatomy, different connectivity. Then there is the cortex, which is the most developed part of the brain in humans. And in the cortex, you have different regions of the cortex that are responsible for vision, for audition, for motor control, for language. Now one of the big puzzles of this is that in the cortex is the cortex, is the cortex, it looks like it is the same in terms of hardware, in terms of type of neurons and connectivity across these different modalities. So for the cortex. Letting aside these other parts of the brain, like spinal cord, hippocampus cerebellum and”
2019-01-19 · Lex Fridman Podcast · Tomaso Poggio: Brains, Minds, and Machines · IDENTIFIED FROM THE TRANSCRIPT · source